© 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. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 12143
    Prev
    Next
    INDEX
    Explanations

    phrases related to a large portion or group

    oai_token-act-pair · gpt-3.5-turbo

    phrases that refer to the concept of a majority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     limbs
    -0.61
    rament
    -0.58
    laden
    -0.57
     convol
    -0.53
    heed
    -0.53
    LV
    -0.53
    ensis
    -0.52
     messenger
    -0.51
    pelled
    -0.51
     greatness
    -0.50
    POSITIVE LOGITS
     of
    1.06
     (>
    0.82
    OF
    0.77
     thereof
    0.76
     Of
    0.73
     OF
    0.72
    of
    0.71
     (~
    0.71
    Of
    0.70
    afa
    0.66
    Activations Density 0.074%

    No Known Activations