© 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 Local
    9. 6-RES_SCL-AJT
    11. 4153
    Prev
    Next
    INDEX
    Explanations

    medical symptoms and conditions

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    288
    +0.19
    0.8%
    447
    +0.16
    0.7%
    515
    +0.15
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.19
    0.21
    10
    +0.16
    0.07
    238
    +0.15
    0.07
    Negative Logits
    akening
    -0.94
    itsch
    -0.92
    ered
    -0.88
    sky
    -0.88
    ork
    -0.83
    yer
    -0.81
    uph
    -0.80
    rahim
    -0.80
    roxy
    -0.79
    hari
    -0.78
    POSITIVE LOGITS
     emulator
    1.26
     terminal
    0.93
    itone
    0.86
     termin
    0.79
     poles
    0.78
     pole
    0.78
    termin
    0.77
    igmatic
    0.77
     Rouge
    0.77
     Termin
    0.75
    Activations Density 10.333%

    No Known Activations