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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 121
    Prev
    Next
    INDEX
    Explanations

    patterns or sequences of numbers

    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
    447
    +0.21
    0.7%
    206
    +0.14
    0.5%
    44
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.21
    0.13
    289
    +0.14
    0.02
    176
    +0.13
    0.06
    Negative Logits
    ĸļ
    -1.04
     arrang
    -1.01
     sidx
    -1.00
    ModLoader
    -0.99
     reconc
    -0.93
     Beir
    -0.93
    azeera
    -0.90
     notor
    -0.86
     Palestin
    -0.86
     neighb
    -0.84
    POSITIVE LOGITS
    tick
    0.99
    Weak
    0.92
    falls
    0.91
    Hyper
    0.90
    Pred
    0.90
    aiden
    0.89
    Remote
    0.86
    Loading
    0.86
    reme
    0.85
    fo
    0.85
    Activations Density 2.337%

    No Known Activations