© 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. 4649
    Prev
    Next
    INDEX
    Explanations

    the word "it" followed by varying contexts and actions

    oai_token-act-pair · gpt-3.5-turbo

    frequent occurrences of the pronoun "it."

    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
     Eighth
    -0.63
    icons
    -0.61
    former
    -0.60
    itatively
    -0.60
    scribe
    -0.59
    izable
    -0.59
     retaining
    -0.59
    anton
    -0.58
    ordinate
    -0.57
     ILCS
    -0.56
    POSITIVE LOGITS
     rains
    1.19
     happened
    1.10
    alian
    1.09
     raining
    1.08
     happens
    1.08
     seems
    1.07
     hurts
    1.04
     dawn
    1.04
     wasn
    1.03
    chy
    1.02
    Activations Density 0.306%

    No Known Activations