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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 4729
    Prev
    Next
    INDEX
    Explanations

    phrases indicating representation or action on someone's behalf

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating representation or advocacy on behalf of groups or individuals

    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
     gorge
    -0.67
    nings
    -0.66
    TEXT
    -0.66
    trap
    -0.64
     dice
    -0.63
    nery
    -0.62
    malink
    -0.62
    heim
    -0.62
     gears
    -0.62
     calculus
    -0.62
    POSITIVE LOGITS
     clients
    0.98
     constituents
    0.86
     multinational
    0.79
     plaintiffs
    0.79
     corporations
    0.78
     individuals
    0.77
     Consumers
    0.76
     companies
    0.74
     entities
    0.74
     Individuals
    0.73
    Activations Density 0.152%

    No Known Activations