© 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. 13677
    Prev
    Next
    INDEX
    Explanations

    phrases related to courage and strength in various contexts

    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
    288
    +0.22
    0.7%
    635
    +0.20
    0.6%
    255
    +0.17
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.22
    0.15
    225
    +0.20
    0.08
    255
    +0.17
    0.08
    Negative Logits
    ORN
    -1.20
    jay
    -1.13
    iewicz
    -1.13
    iverse
    -1.05
    emis
    -0.98
    oval
    -0.94
    eor
    -0.93
    onal
    -0.93
    joining
    -0.92
    oan
    -0.91
    POSITIVE LOGITS
    ously
    1.65
    uous
    1.26
    acies
    1.10
    uously
    1.10
    ively
    1.09
     persever
    1.07
     courage
    1.04
    ibilities
    1.02
    ieve
    1.02
    fulness
    0.96
    Activations Density 2.024%

    No Known Activations