© 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. 8-RES-JB
    11. 7600
    Prev
    Next
    INDEX
    Explanations

    references to information technology (IT)

    oai_token-act-pair · gpt-3.5-turbo

    references to IT (Information Technology) and related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itives
    -0.74
    ktop
    -0.74
    terday
    -0.69
    lets
    -0.62
    liest
    -0.59
    ãĥ£
    -0.58
    hyde
    -0.57
    abouts
    -0.56
    ————————————————
    -0.56
    ãĥ©ãĥ³
    -0.56
    POSITIVE LOGITS
    IME
    1.10
    EMS
    1.04
    unes
    1.02
    MIN
    0.97
    ECH
    0.88
    LA
    0.86
    FW
    0.85
    TO
    0.85
    ILA
    0.84
    YP
    0.84
    Activations Density 0.024%

    No Known Activations