© 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. 926
    Prev
    Next
    INDEX
    Explanations

    contrasting aspects or comparisons within texts

    oai_token-act-pair · gpt-3.5-turbo

    expressions that highlight contrasts and comparisons

    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
    "},"
    -0.61
     bye
    -0.58
     Himself
    -0.58
    #$
    -0.58
    dr
    -0.58
     kinda
    -0.57
    Sund
    -0.56
     vert
    -0.56
     americ
    -0.56
     merge
    -0.55
    POSITIVE LOGITS
    ccording
    0.79
    ,.
    0.77
    ,
    0.77
    ebus
    0.73
    .,
    0.64
    adays
    0.63
    acket
    0.63
    è£ħ
    0.63
    cially
    0.61
    itia
    0.61
    Activations Density 0.224%

    No Known Activations