Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 5327
    Prev
    Next
    INDEX
    Explanations

    phrases related to societal issues and impacts

    oai_token-act-pair · gpt-3.5-turbo

    items related to social or cultural values and criticisms

    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
    ajor
    -0.85
    scribe
    -0.80
    wark
    -0.79
    uca
    -0.78
    oru
    -0.77
    instance
    -0.77
    alion
    -0.76
    ocument
    -0.75
    dule
    -0.74
    escription
    -0.73
    POSITIVE LOGITS
     lousy
    1.05
     sluggish
    1.02
     lack
    1.01
     penchant
    1.00
     inability
    0.99
     scant
    0.98
     lackluster
    0.97
     catchy
    0.95
     inexplicable
    0.95
     dismal
    0.95
    Activations Density 0.380%

    No Known Activations