© 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. 1-RES-JB
    11. 3107
    Prev
    Next
    INDEX
    Explanations

    words related to additional information or actions beyond the main context

    oai_token-act-pair · gpt-3.5-turbo

    the word "also" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jam
    -0.72
    agus
    -0.70
    acious
    -0.69
    heat
    -0.68
    ash
    -0.67
    ASE
    -0.67
    enter
    -0.66
     Chaser
    -0.65
    Earth
    -0.61
     Bout
    -0.60
    POSITIVE LOGITS
     includ
    0.89
     includes
    0.82
     cautioned
    0.80
     anecd
    0.79
     noteworthy
    0.78
     occasionally
    0.75
     included
    0.74
     congratulated
    0.74
     optionally
    0.73
     contributed
    0.72
    Activations Density 0.094%

    No Known Activations