© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 12083
    Prev
    Next
    INDEX
    Explanations

    salient points in discussions or arguments, particularly those related to analysis and critique

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    679
    +0.17
    0.7%
    447
    +0.13
    0.5%
    638
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    679
    +0.17
    0.10
    195
    +0.13
    0.04
    540
    +0.12
    0.09
    Negative Logits
    esi
    -0.88
     sweats
    -0.83
    osa
    -0.81
     throats
    -0.79
    bia
    -0.78
    ictionary
    -0.77
    upiter
    -0.77
    usra
    -0.76
    yss
    -0.75
    aline
    -0.74
    POSITIVE LOGITS
     pertaining
    0.99
    :-
    0.98
    \":
    0.86
     regarding
    0.86
     relating
    0.82
     Valiant
    0.82
    :'
    0.81
     transpired
    0.81
     viz
    0.79
    ":[{"
    0.77
    Activations Density 0.997%

    No Known Activations