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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 9-RES-JB
    6. 21435
    Prev
    Next
    INDEX
    Explanations

    profane terms or strong language

    oai_token-act-pair · gpt-3.5-turbo

    explicit language and strong profanity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     elig
    -0.73
     conduc
    -0.69
    Buyable
    -0.67
    utterstock
    -0.63
     ancest
    -0.63
     Nav
    -0.63
     mosqu
    -0.62
    è£ħ
    -0.62
     isolation
    -0.61
     accomp
    -0.61
    POSITIVE LOGITS
    tty
    1.17
    cking
    1.13
    gger
    1.08
    shit
    1.08
    kers
    1.05
    king
    1.05
    holes
    1.03
    tch
    1.02
    hole
    1.00
    cks
    0.99
    Activations Density 0.108%

    No Known Activations