© 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. 7-RES-JB
    11. 16793
    Prev
    Next
    INDEX
    Explanations

    pronouns related to a male subject

    oai_token-act-pair · gpt-3.5-turbo

    references to male characters in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CNN
    -0.77
     Bundes
    -0.73
     Mae
    -0.71
    nb
    -0.65
    Temperature
    -0.64
     sovere
    -0.64
     Period
    -0.64
    mary
    -0.62
     Thatcher
    -0.62
    WN
    -0.62
    POSITIVE LOGITS
     penis
    0.86
     semen
    0.84
     handsome
    0.83
     ejac
    0.81
     dick
    0.80
     circumcised
    0.80
     sperm
    0.77
    avier
    0.76
     cock
    0.75
    don
    0.75
    Activations Density 0.269%

    No Known Activations