© 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. 6-RES-JB
    11. 20258
    Prev
    Next
    INDEX
    Explanations

    words related to separation or extraction

    oai_token-act-pair · gpt-3.5-turbo

    suffixes related to psychological or emotional conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Clover
    -0.65
     arteries
    -0.62
    steen
    -0.59
     Pryor
    -0.59
     Larson
    -0.58
     Twe
    -0.58
     Garland
    -0.57
     Awakens
    -0.56
    ako
    -0.56
     Cyrus
    -0.55
    POSITIVE LOGITS
    olated
    0.84
    URA
    0.80
    uras
    0.79
    lishes
    0.78
    urized
    0.77
    cit
    0.77
    hibited
    0.75
    aneous
    0.75
    atorium
    0.73
    ciation
    0.73
    Activations Density 0.071%

    No Known Activations