© 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. 0-RES-JB
    11. 22723
    Prev
    Next
    INDEX
    Explanations

    mentions of specific names or places followed by the word "horn" or "shop"

    oai_token-act-pair · gpt-3.5-turbo

    specific references to shops or commercial establishments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     laps
    -0.70
     dissent
    -0.67
     Alph
    -0.63
     values
    -0.63
     typing
    -0.62
     dB
    -0.61
     defaults
    -0.59
     Values
    -0.59
     outl
    -0.59
     cross
    -0.59
    POSITIVE LOGITS
    shop
    2.75
    horn
    2.45
    Shop
    1.65
    shi
    1.54
    strap
    1.31
    iard
    1.12
    houses
    0.99
    store
    0.97
    stri
    0.96
    manship
    0.96
    Activations Density 0.036%

    No Known Activations