© 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. 1-RES-JB
    11. 20057
    Prev
    Next
    INDEX
    Explanations

    specific details or descriptions in texts

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize thoroughness or extensive description

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onz
    -0.82
     Sabha
    -0.72
    inventoryQuantity
    -0.70
    ammy
    -0.68
    ammers
    -0.65
    alg
    -0.64
    anski
    -0.64
     Balanced
    -0.63
    nee
    -0.62
    Tube
    -0.62
    POSITIVE LOGITS
     detail
    1.43
     details
    1.22
     Detail
    1.04
    details
    0.92
     particulars
    0.89
     Details
    0.87
    detail
    0.85
     specifics
    0.85
     descriptions
    0.85
     detailing
    0.83
    Activations Density 0.011%

    No Known Activations