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. 10-RES-JB
    6. 16873
    Prev
    Next
    INDEX
    Explanations

    technical terms or language related to contracts, obligations, and specific requirements

    oai_token-act-pair · gpt-3.5-turbo

    the presence of high-stakes situations or critical issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     stem
    -0.97
     fallout
    -0.86
     rul
    -0.86
     paddle
    -0.85
     censored
    -0.85
     star
    -0.84
     doomed
    -0.84
     raft
    -0.84
     hatch
    -0.84
     ripple
    -0.84
    POSITIVE LOGITS
    Prov
    1.76
    Individual
    1.67
    Compl
    1.66
    Physical
    1.66
    Anything
    1.65
    Contin
    1.64
    Use
    1.64
    Any
    1.64
    Used
    1.64
    Increased
    1.63
    Activations Density 0.219%

    No Known Activations