© 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. 3-RES-JB
    11. 22595
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to situations or actions that are understandable or justifiable

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with the concept of being understandable

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    apixel
    -0.79
    berman
    -0.78
    ammy
    -0.78
    hips
    -0.76
    rieg
    -0.76
    elope
    -0.72
    eng
    -0.72
    rolog
    -0.71
    rology
    -0.71
    jay
    -0.71
    POSITIVE LOGITS
     understandable
    0.95
     incomp
    0.71
     indignation
    0.71
     impat
    0.69
     repentance
    0.69
     unanim
    0.69
     partName
    0.69
     Mellon
    0.68
     prompts
    0.68
     "$:/
    0.67
    Activations Density 0.009%

    No Known Activations