© 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. 3940
    Prev
    Next
    INDEX
    Explanations

    advice or suggestions related to different aspects of life

    oai_token-act-pair · gpt-3.5-turbo

    instances of social commentary and condition descriptions

    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
     Previously
    -0.78
    ãĤ¶
    -0.74
    igslist
    -0.74
     Earlier
    -0.70
    arag
    -0.68
    bis
    -0.68
    jri
    -0.66
    Previously
    -0.66
    Second
    -0.66
    Hide
    -0.65
    POSITIVE LOGITS
     whichever
    0.95
     ALWAYS
    0.92
     whatever
    0.82
     regardless
    0.79
     invariably
    0.79
     always
    0.79
    whatever
    0.76
     irrespective
    0.72
     damned
    0.71
     whatsoever
    0.69
    Activations Density 0.314%

    No Known Activations