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. 0-RES-JB
    6. 3373
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of being resistant to damage or harm

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "proof" and its variations

    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
    ets
    -0.68
     cho
    -0.65
     affiliates
    -0.64
     quer
    -0.63
     Sector
    -0.63
     ms
    -0.62
    ETS
    -0.61
     Middle
    -0.60
     beet
    -0.60
     Mare
    -0.59
    POSITIVE LOGITS
    proof
    4.56
    Proof
    2.63
     proof
    2.20
     Proof
    2.16
    resistant
    1.69
     proofs
    1.53
    evidence
    1.33
    safe
    1.15
    tight
    1.01
    proven
    0.97
    Activations Density 0.014%

    No Known Activations