© 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. 6-RES-JB
    11. 12871
    Prev
    Next
    INDEX
    Explanations

    expressions related to family relationships

    oai_token-act-pair · gpt-3.5-turbo

    descriptors that denote qualities or states of being

    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
    ilater
    -0.89
    ãĥ¯ãĥ³
    -0.88
    igent
    -0.80
    href
    -0.80
    itect
    -0.77
     Gutenberg
    -0.75
    iguous
    -0.74
    ileaks
    -0.74
    rawdownloadcloneembedreportprint
    -0.73
    ADRA
    -0.72
    POSITIVE LOGITS
    puff
    1.01
    tics
    0.95
    rics
    0.79
    pha
    0.79
    ffe
    0.76
    zed
    0.73
    cemic
    0.71
     slopes
    0.69
    cos
    0.68
    tons
    0.67
    Activations Density 0.035%

    No Known Activations