© 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 EvalsExportsinterp-engineNEWAPI 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. 7201
    Prev
    Next
    INDEX
    Explanations

    references to a specific name, "Mignola"

    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
    4
    +0.15
    0.5%
    167
    +0.15
    0.5%
    746
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.15
    0.07
    326
    +0.15
    0.06
    4
    +0.15
    0.05
    Negative Logits
    bian
    -0.98
    cham
    -0.94
     Mighty
    -0.88
    HAHAHAHA
    -0.87
    RC
    -0.85
     Nex
    -0.84
     Springfield
    -0.83
    ------------------------------------------------
    -0.81
    successfully
    -0.81
    UNCH
    -0.81
    POSITIVE LOGITS
    ments
    1.57
    ificant
    1.53
    antly
    1.45
    mentation
    1.29
    entials
    1.29
    ancy
    1.27
    opol
    1.26
    eous
    1.23
    essee
    1.22
    ame
    1.22
    Activations Density 0.879%

    No Known Activations