© 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. 2823
    Prev
    Next
    INDEX
    Explanations

    terms related to chemistry and materials science

    oai_token-act-pair · gpt-3.5-turbo

    terms related to scientific disciplines, particularly chemistry and its applications

    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
     bear
    -0.66
     recurring
    -0.64
     Tig
    -0.64
     ell
    -0.63
     spaced
    -0.61
     tend
    -0.61
     poor
    -0.61
     obese
    -0.59
     rid
    -0.58
     bye
    -0.58
    POSITIVE LOGITS
    istry
    4.86
    istries
    2.14
    istration
    1.42
    isters
    1.37
    ifice
    1.33
    ister
    1.28
    ists
    1.22
    istics
    1.18
    ificate
    1.16
    smanship
    1.15
    Activations Density 0.016%

    No Known Activations