© 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. 1371
    Prev
    Next
    INDEX
    Explanations

    economic and financial figures and comparisons

    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
    313
    +0.15
    0.5%
    202
    +0.14
    0.5%
    235
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    718
    +0.15
    0.09
    529
    +0.14
    0.07
    566
    +0.14
    0.07
    Negative Logits
    ogly
    -0.97
     motif
    -0.92
    abre
    -0.86
    76561
    -0.85
     Tick
    -0.84
    âĢIJ
    -0.83
    atana
    -0.82
     Cosponsors
    -0.82
    enos
    -0.81
     disputes
    -0.81
    POSITIVE LOGITS
    rounded
    1.05
     existed
    1.02
     wiser
    0.99
     gotten
    0.98
     listened
    0.94
     hindsight
    0.94
    oppers
    0.93
     tomorrow
    0.93
    vana
    0.90
     Polly
    0.90
    Activations Density 2.401%

    No Known Activations