© 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. 117
    Prev
    Next
    INDEX
    Explanations

    locations and distances specified in miles

    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
    344
    +0.18
    0.6%
    57
    +0.18
    0.6%
    649
    +0.17
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    238
    +0.18
    0.06
    344
    +0.18
    0.06
    537
    +0.17
    0.05
    Negative Logits
    */(
    -1.11
    itol
    -1.07
    gotten
    -1.06
    icum
    -1.04
    itative
    -1.04
    istry
    -1.04
    ured
    -1.01
    orum
    -1.00
    icer
    -0.99
    olith
    -0.98
    POSITIVE LOGITS
    bike
    1.25
     kilometers
    1.24
     radius
    1.18
     km
    1.18
     kilometres
    1.08
    km
    1.05
    assing
    1.05
     miles
    1.04
     Cheong
    1.03
     traveled
    1.03
    Activations Density 0.650%

    No Known Activations