© 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. 10-RES-JB
    11. 6869
    Prev
    Next
    INDEX
    Explanations

    names of individuals, particularly in official or formal contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to notable individuals and their actions or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     erection
    -0.80
     dick
    -0.71
    jandro
    -0.71
     foreskin
    -0.68
     prostate
    -0.68
    enhagen
    -0.68
    cko
    -0.67
     skelet
    -0.65
     Jr
    -0.64
     Jonah
    -0.64
    POSITIVE LOGITS
     herself
    2.00
     husband
    1.18
    kaya
    1.08
     she
    1.07
     She
    1.05
     hijab
    1.05
     SHE
    1.04
     heroine
    1.03
     her
    1.02
    She
    1.02
    Activations Density 0.722%

    No Known Activations