© 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. 22268
    Prev
    Next
    INDEX
    Explanations

    profane language

    oai_token-act-pair · gpt-3.5-turbo

    instances of strong profanity and expressions of frustration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    olor
    -0.81
    raft
    -0.73
    ward
    -0.70
     �
    -0.69
    rift
    -0.69
    lus
    -0.63
    Analysis
    -0.63
    alyst
    -0.62
     Reporter
    -0.60
    holder
    -0.60
    POSITIVE LOGITS
     fucking
    3.70
     goddamn
    3.29
     fuckin
    2.90
     freaking
    2.53
     godd
    2.39
     damn
    2.20
     FUCK
    2.19
     fucked
    1.92
     Godd
    1.88
     shitty
    1.87
    Activations Density 0.025%

    No Known Activations