© 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. 3-RES-JB
    11. 3101
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports events and game actions

    oai_token-act-pair · gpt-3.5-turbo

    instances of punctuation, specifically commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    riet
    -0.79
    emin
    -0.78
    reprene
    -0.72
    ulz
    -0.71
    anchester
    -0.71
    sth
    -0.69
    uscript
    -0.67
    isure
    -0.65
    sylv
    -0.64
    itarian
    -0.63
    POSITIVE LOGITS
     coached
    0.97
     albeit
    0.96
     namely
    0.86
     barring
    0.84
     Bengals
    0.81
     fullback
    0.81
    76561
    0.79
     undrafted
    0.78
     although
    0.78
     Kobe
    0.77
    Activations Density 0.457%

    No Known Activations