© 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. 16562
    Prev
    Next
    INDEX
    Explanations

    sentences starting with "It" and "For his 1st place finish in the Prototype class."

    oai_token-act-pair · gpt-3.5-turbo

    instances 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
    itatively
    -0.59
     immersion
    -0.57
    hips
    -0.57
    ************
    -0.56
    ————————
    -0.56
    ------------
    -0.55
    */
    -0.55
    tile
    -0.54
     Eighth
    -0.54
    scribe
    -0.53
    POSITIVE LOGITS
    zbollah
    1.06
     rains
    1.02
     Begins
    0.95
    iner
    0.94
    chwitz
    0.92
     transpired
    0.89
     seems
    0.89
     dawn
    0.88
     wasn
    0.87
    asca
    0.87
    Activations Density 0.119%

    No Known Activations