© 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. 19772
    Prev
    Next
    INDEX
    Explanations

    positive comments and affirmations

    oai_token-act-pair · gpt-3.5-turbo

    sentences that express strong emotional sentiments or impactful statements

    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
    arching
    -0.74
     Afgh
    -0.73
    */
    -0.70
     */
    -0.70
     arisen
    -0.69
     conver
    -0.65
    endi
    -0.65
    ĵĺ
    -0.64
    frequency
    -0.63
    etheless
    -0.63
    POSITIVE LOGITS
     quotes
    0.86
    Said
    0.85
    yrics
    0.80
     "...
    0.78
    omsky
    0.75
     reply
    0.75
     referring
    0.70
     quotation
    0.70
     replied
    0.69
    upon
    0.69
    Activations Density 0.518%

    No Known Activations