© 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. 10-RES-JB
    11. 17458
    Prev
    Next
    INDEX
    Explanations

    terms related to inquiries or investigations

    oai_token-act-pair · gpt-3.5-turbo

    words related to inquiries or investigations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    har
    -0.68
     Beet
    -0.66
     Depend
    -0.66
    stadt
    -0.64
    enburg
    -0.62
    ingham
    -0.61
    comb
    -0.61
     Magicka
    -0.60
    alone
    -0.60
    Ĥ¬
    -0.60
    POSITIVE LOGITS
     probing
    1.10
     into
    1.04
     inquire
    1.01
    iry
    0.98
    naires
    0.98
     inqu
    0.94
     INTO
    0.94
    prising
    0.92
    into
    0.92
     questions
    0.90
    Activations Density 0.073%

    No Known Activations