© 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. 7944
    Prev
    Next
    INDEX
    Explanations

    descriptions or mentions of different versions of something

    oai_token-act-pair · gpt-3.5-turbo

    references to different versions of products, works, or documents

    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
     Institution
    -0.70
    ndra
    -0.66
    amus
    -0.66
    ocracy
    -0.63
    frey
    -0.62
     appointment
    -0.62
    cence
    -0.61
    isition
    -0.61
    undrum
    -0.60
     CONTIN
    -0.60
    POSITIVE LOGITS
     versions
    3.67
     editions
    2.27
     version
    2.06
     variants
    2.05
     iterations
    1.90
     copies
    1.84
    Versions
    1.75
     varieties
    1.60
    versions
    1.59
     equivalents
    1.58
    Activations Density 0.023%

    No Known Activations