© 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. 13698
    Prev
    Next
    INDEX
    Explanations

    references to inevitability and future events

    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
    151
    +0.18
    0.6%
    326
    +0.17
    0.6%
    633
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    151
    +0.18
    0.11
    724
    +0.17
    0.08
    551
    +0.15
    0.05
    Negative Logits
    nan
    -1.25
    burgh
    -1.16
    vest
    -1.16
    tein
    -1.14
    rief
    -1.09
    chel
    -1.05
    rations
    -1.05
    raph
    -1.04
    fil
    -1.03
    liter
    -1.03
    POSITIVE LOGITS
    ministic
    1.38
     culmin
    1.16
     consequence
    1.11
     arises
    1.07
     inflic
    1.07
     grav
    1.06
     dissip
    1.06
     coincide
    1.05
     occurring
    1.03
     evolve
    1.01
    Activations Density 1.150%

    No Known Activations