© 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. 4-RES-JB
    11. 14822
    Prev
    Next
    INDEX
    Explanations

    words related to physical injuries or pain

    oai_token-act-pair · gpt-3.5-turbo

    words related to various types of food and their preparation methods

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

    No Comments

    Negative Logits
    acqu
    -0.78
     Samar
    -0.63
    iage
    -0.62
     rave
    -0.58
     Aur
    -0.58
    ku
    -0.57
     raise
    -0.56
    recomm
    -0.56
     resolution
    -0.54
    iazep
    -0.54
    POSITIVE LOGITS
    xus
    0.82
    atism
    0.79
    Sport
    0.67
    othy
    0.65
    acus
    0.65
    ulent
    0.63
    ulence
    0.63
     Obj
    0.62
    å°Ĩ
    0.62
    ombat
    0.62
    Activations Density 0.059%

    No Known Activations