© 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. 3159
    Prev
    Next
    INDEX
    Explanations

    numbers or figures with units, including currency symbols and percentages

    oai_token-act-pair · gpt-3.5-turbo

    numeric values and their formatting

    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
    gerald
    -0.67
    awaru
    -0.67
    lehem
    -0.65
    rolet
    -0.65
    ians
    -0.62
    ured
    -0.62
     "$:/
    -0.61
    iership
    -0.59
    uine
    -0.59
    etz
    -0.59
    POSITIVE LOGITS
    nd
    1.98
    ND
    1.12
    160
    1.02
    133
    1.02
    147
    1.01
     thirds
    0.97
    187
    0.95
     externalToEVAOnly
    0.92
    ½
    0.92
    245
    0.90
    Activations Density 0.130%

    No Known Activations