© 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. 4-RES-JB
    11. 20508
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to personal or individual identity

    oai_token-act-pair · gpt-3.5-turbo

    references to identity-related concepts or issues

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

    No Comments

    Negative Logits
    oys
    -0.68
     Vaj
    -0.66
    ittle
    -0.65
    ithing
    -0.64
    990
    -0.64
    iths
    -0.64
     Pigs
    -0.63
    housing
    -0.63
    wolves
    -0.61
     Spoon
    -0.59
    POSITIVE LOGITS
    entity
    0.98
     identity
    0.95
    iosyncr
    0.92
     identities
    0.91
     Identity
    0.91
     è£ıè
    0.87
     Theft
    0.87
    ativity
    0.80
    idas
    0.77
     theft
    0.72
    Activations Density 0.023%

    No Known Activations