© 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. 6-RES-JB
    11. 15223
    Prev
    Next
    INDEX
    Explanations

    pronouns and possessive pronouns referring to male individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific male individual

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    grave
    -0.69
     è£ıè
    -0.67
     Pwr
    -0.66
     Nationwide
    -0.65
    igmatic
    -0.64
    assing
    -0.64
    DAY
    -0.63
    arios
    -0.63
    reshold
    -0.63
    ylon
    -0.63
    POSITIVE LOGITS
    'll
    0.97
     Majesty
    0.93
    zbollah
    0.92
    'd
    0.87
     knows
    0.85
     hates
    0.85
     thinks
    0.82
     cheated
    0.82
     didnt
    0.82
     loves
    0.82
    Activations Density 0.222%

    No Known Activations