© 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. 1-RES-JB
    11. 20372
    Prev
    Next
    INDEX
    Explanations

    words related to sports entities or personalities

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Sto" and variations related to "Sta," indicating a focus on a particular brand or group associated with those terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MAL
    -0.79
    bid
    -0.73
    URI
    -0.73
    ITNESS
    -0.72
    intosh
    -0.67
    ateur
    -0.66
    Leaks
    -0.65
    ATIONAL
    -0.65
    LESS
    -0.64
    enance
    -0.64
    POSITIVE LOGITS
     Sto
    1.13
    pped
    0.96
    pping
    0.87
    zzi
    0.77
    icism
    0.72
     resil
    0.69
    iazep
    0.69
    agher
    0.68
    ved
    0.68
    opa
    0.67
    Activations Density 0.009%

    No Known Activations