© 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. 13439
    Prev
    Next
    INDEX
    Explanations

    the word "body" followed by either a number or an action

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "body."

    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
     FEC
    -0.66
     Kafka
    -0.65
     Nex
    -0.63
     Dickens
    -0.63
     precip
    -0.60
     Democr
    -0.58
     perfect
    -0.57
     Synd
    -0.57
     Clover
    -0.57
     Griffith
    -0.56
    POSITIVE LOGITS
    body
    1.42
    guards
    1.09
    builder
    1.00
    weight
    0.95
    bags
    0.92
    guard
    0.90
    bag
    0.87
    building
    0.85
    anguage
    0.84
    hood
    0.84
    Activations Density 0.006%

    No Known Activations