© 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. 8-RES-JB
    11. 18747
    Prev
    Next
    INDEX
    Explanations

    verbs that describe or portray something

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the act of describing various subjects or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    assi
    -0.68
    umo
    -0.65
    acus
    -0.61
    vernment
    -0.61
    alos
    -0.60
    ammy
    -0.60
    ci
    -0.58
    iasm
    -0.58
    oner
    -0.57
    ground
    -0.57
    POSITIVE LOGITS
     descriptions
    0.77
     how
    0.73
     Patterns
    0.73
    urated
    0.72
     patterns
    0.71
     qualities
    0.71
    enance
    0.70
     aloud
    0.69
    ãĤ¢ãĥ«
    0.68
    ribing
    0.67
    Activations Density 0.061%

    No Known Activations