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

    Neuronpedia

    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. 9937
    Prev
    Next
    INDEX
    Explanations

    occupations or roles related to specific industries

    oai_token-act-pair · gpt-3.5-turbo

    terms related to roles, positions, or classifications in various contexts

    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
     Klux
    -0.79
    ãĥĥãĥī
    -0.78
    ãĥ©ãĥ³
    -0.72
    sung
    -0.65
     pathological
    -0.63
     destruct
    -0.61
    ãĥķãĤ©
    -0.60
    ãĥ¼ãĥ«
    -0.60
    vell
    -0.59
    omo
    -0.59
    POSITIVE LOGITS
    hips
    0.89
     designation
    0.85
     basis
    0.79
     pursuant
    0.79
    elist
    0.72
     slot
    0.71
    endment
    0.69
     consisting
    0.68
     ineligible
    0.67
    hip
    0.67
    Activations Density 0.555%

    No Known Activations