© 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. 5588
    Prev
    Next
    INDEX
    Explanations

    body parts, particularly those related to communication functions

    oai_token-act-pair · gpt-3.5-turbo

    references to body parts and metaphoric expressions involving human anatomy

    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
     Virus
    -0.68
     Naz
    -0.67
    rip
    -0.66
     Rogue
    -0.66
     disturbance
    -0.65
    Rogue
    -0.62
    ron
    -0.62
    Net
    -0.62
     Zionist
    -0.61
    killer
    -0.60
    POSITIVE LOGITS
    poons
    1.09
    chool
    1.07
    mith
    1.05
    ettings
    1.01
    hops
    0.99
    paces
    0.99
    ynthesis
    0.97
    pots
    0.96
    etting
    0.96
    uggest
    0.95
    Activations Density 0.066%

    No Known Activations