© 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. 3639
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific group of people or entities

    oai_token-act-pair · gpt-3.5-turbo

    references to groups or audiences

    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
    Director
    -0.76
    Dialog
    -0.71
    orial
    -0.69
    Plot
    -0.67
    forth
    -0.67
    Dust
    -0.66
    enegger
    -0.66
    grass
    -0.64
    Dep
    -0.63
    ãģ®å
    -0.62
    POSITIVE LOGITS
     sake
    0.98
     wishing
    0.89
     guessed
    0.80
     wanting
    0.78
     purposes
    0.77
    ufact
    0.75
     attending
    0.74
     unfamiliar
    0.73
     redes
    0.73
     interested
    0.72
    Activations Density 0.086%

    No Known Activations