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

    Neuronpedia

    APICircuit 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. 9-RES-JB
    6. 4349
    Prev
    Next
    INDEX
    Explanations

    instances where something or someone is prohibited or banned from doing something

    oai_token-act-pair · gpt-3.5-turbo

    instances of being banned or prohibited

    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
    framework
    -0.81
    hematic
    -0.74
    reset
    -0.72
    engine
    -0.70
    cule
    -0.70
    bent
    -0.70
    arity
    -0.70
    uid
    -0.69
    bard
    -0.69
    rors
    -0.67
    POSITIVE LOGITS
     entering
    1.21
     accessing
    1.19
     owning
    1.02
     participating
    0.99
     joining
    0.99
     possessing
    0.99
     contacting
    0.97
     attending
    0.97
     appearing
    0.94
     donating
    0.91
    Activations Density 0.083%

    No Known Activations