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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 1-RES-JB
    6. 19524
    Prev
    Next
    INDEX
    Explanations

    phrases about testimonies in a legal setting

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word 'testified' and its variations in context

    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
    uber
    -0.77
    nick
    -0.73
    obs
    -0.71
    bern
    -0.70
    holy
    -0.69
    erm
    -0.67
    elf
    -0.66
    itar
    -0.66
    liber
    -0.66
    culture
    -0.65
    POSITIVE LOGITS
     testified
    1.36
     testifying
    1.23
     testify
    1.16
     testimony
    1.11
     testimonies
    1.06
    ĸļ
    0.96
     hearings
    0.91
     witnesses
    0.90
     conclud
    0.88
     Cosponsors
    0.86
    Activations Density 0.008%

    No Known Activations