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. 7-RES-JB
    6. 3423
    Prev
    Next
    INDEX
    Explanations

    references to people testifying in various situations

    oai_token-act-pair · gpt-3.5-turbo

    references to legal testimony and witness statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ahime
    -0.79
    tails
    -0.76
    fly
    -0.73
    tail
    -0.73
    rave
    -0.71
     Chop
    -0.69
    vier
    -0.68
     Hebdo
    -0.66
    pop
    -0.65
    flies
    -0.64
    POSITIVE LOGITS
     testimony
    1.28
     testimonies
    1.19
     testifying
    1.15
     testify
    1.10
     examiner
    1.03
    imony
    1.02
     testified
    0.95
     hearings
    0.94
     deposition
    0.89
     witness
    0.87
    Activations Density 0.050%

    No Known Activations