© 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. 1-RES-JB
    11. 3251
    Prev
    Next
    INDEX
    Explanations

    terms related to prohibition or things that are not allowed

    oai_token-act-pair · gpt-3.5-turbo

    instances and contexts of the word "forbidden."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sonian
    -1.05
    etitive
    -0.82
    ulative
    -0.79
    ocker
    -0.78
    okane
    -0.78
    iets
    -0.76
    ersed
    -0.76
    Seattle
    -0.75
    =-=-=-=-
    -0.73
    izational
    -0.73
    POSITIVE LOGITS
    bidden
    1.18
     forbidden
    1.10
     forbid
    1.03
     forb
    0.93
     Forbidden
    0.91
    ĸļ
    0.87
     fruit
    0.80
     forbids
    0.78
     confir
    0.72
     taboo
    0.71
    Activations Density 0.012%

    No Known Activations