© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4-RES-JB
    11. 12164
    Prev
    Next
    INDEX
    Explanations

    phrases mentioning strong support or opposition towards a particular subject or policy

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate support or opposition to various subjects or entities

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

    No Comments

    Negative Logits
    hole
    -0.65
    few
    -0.60
     istg
    -0.60
    holes
    -0.59
     lapse
    -0.57
     ];
    -0.57
    phabet
    -0.57
     equivalents
    -0.56
    igmatic
    -0.55
    uria
    -0.54
    POSITIVE LOGITS
     theirs
    0.77
     sorts
    0.75
    ãĤ¯
    0.75
     ours
    0.69
    ãĤ¦
    0.69
    thood
    0.68
     incumb
    0.67
    irie
    0.65
    emale
    0.65
     dissent
    0.64
    Activations Density 0.190%

    No Known Activations