© 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. 0-RES-JB
    11. 16487
    Prev
    Next
    INDEX
    Explanations

    phrases related to sexual content

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Freeze
    -0.73
     Maple
    -0.70
    åī
    -0.69
     Alert
    -0.69
    âģ
    -0.68
    artifacts
    -0.66
    ews
    -0.66
    [_
    -0.66
    Ing
    -0.65
     Logged
    -0.64
    POSITIVE LOGITS
     sex
    3.77
     Sex
    2.92
    Sex
    2.73
    sex
    2.52
     sexual
    2.39
    Sexual
    2.06
     Sexual
    2.05
     sexuality
    2.05
     sexes
    2.02
     sexually
    1.96
    Activations Density 0.021%

    No Known Activations