© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 9-RES-JB
    11. 18351
    Prev
    Next
    INDEX
    Explanations

    phrases related to evaluation, assessment, or examination

    oai_token-act-pair · gpt-3.5-turbo

    processes and actions related to evaluation, approval, and utilization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    habi
    -0.58
    olated
    -0.58
     penal
    -0.56
    mare
    -0.55
    lete
    -0.55
     nutshell
    -0.54
    cept
    -0.53
    orious
    -0.53
    pat
    -0.53
    Sequ
    -0.53
    POSITIVE LOGITS
     purposes
    1.84
     sake
    1.34
     reasons
    1.14
    ummies
    0.96
     purpose
    0.90
    EngineDebug
    0.89
    farious
    0.75
    okers
    0.71
     seekers
    0.71
     sometime
    0.69
    Activations Density 0.369%

    No Known Activations