© 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
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 13672
    Prev
    Next
    INDEX
    Explanations

    medical terms related to the cardiovascular system, including arteries and blood vessels

    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
    644
    +0.15
    0.7%
    699
    +0.13
    0.6%
    571
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.15
    0.26
    326
    +0.13
    0.22
    699
    +0.11
    0.03
    Negative Logits
    ety
    -0.83
    asted
    -0.77
    hare
    -0.71
    -+-+-+-+
    -0.71
    gradation
    -0.70
    cott
    -0.70
    udeb
    -0.69
    hots
    -0.68
    %]
    -0.67
    sat
    -0.67
    POSITIVE LOGITS
     vessels
    1.07
     vessel
    0.99
     Vessel
    0.98
     endot
    0.96
     circ
    0.81
     artery
    0.79
     Immortal
    0.76
    esthesia
    0.76
    lia
    0.75
    icularly
    0.74
    Activations Density 7.705%

    No Known Activations