© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 20047
    Prev
    Next
    INDEX
    Explanations

    specific terrorist groups such as the Kurdistan Workers' Party, PKK, and Gulen

    oai_token-act-pair · gpt-3.5-turbo

    references to political groups or parties

    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
    amental
    -0.82
    pu
    -0.79
    pron
    -0.66
    ROR
    -0.66
    photos
    -0.64
     ti
    -0.63
     warr
    -0.63
    åº
    -0.63
     chic
    -0.62
    erial
    -0.62
    POSITIVE LOGITS
     Nash
    0.83
     Kern
    0.69
    essen
    0.69
    ays
    0.68
     Duty
    0.68
    Notes
    0.66
     Fay
    0.65
     Straw
    0.64
    Afee
    0.61
     Sans
    0.61
    Activations Density 0.000%

    No Known Activations