© 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. 7-RES-JB
    11. 15685
    Prev
    Next
    INDEX
    Explanations

    scientific and biological terms or concepts

    oai_token-act-pair · gpt-3.5-turbo

    terms and concepts related to scientific and biological research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Dot
    -0.68
     Nationals
    -0.63
    semble
    -0.62
    owners
    -0.61
    holder
    -0.60
    agall
    -0.60
     peaks
    -0.59
    doms
    -0.58
     Favor
    -0.58
     Faces
    -0.58
    POSITIVE LOGITS
    ysis
    0.89
    aceutical
    0.83
    iologist
    0.79
    Medical
    0.78
    minecraft
    0.78
     cure
    0.75
    onics
    0.75
    bath
    0.74
    iological
    0.73
    Cola
    0.72
    Activations Density 0.418%

    No Known Activations