Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 5540
    Prev
    Next
    INDEX
    Explanations

    instances of the word "sex"

    oai_token-act-pair · gpt-3.5-turbo

    references to sexual activity

    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
    umbs
    -0.63
     Bei
    -0.63
    xtap
    -0.60
    umbing
    -0.60
    otech
    -0.59
     Barcl
    -0.58
     Hil
    -0.57
     IOC
    -0.57
     stru
    -0.56
     Meyer
    -0.56
    POSITIVE LOGITS
    hesda
    0.78
     whilst
    0.76
    thood
    0.72
     with
    0.71
     peacefully
    0.69
     :)
    0.69
     while
    0.68
     abroad
    0.66
     WITHOUT
    0.66
     ;)
    0.66
    Activations Density 0.099%

    No Known Activations