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. 3465
    Prev
    Next
    INDEX
    Explanations

    concepts related to legal or financial responsibility

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "liability" and related terms regarding legal and financial responsibilities

    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
    fast
    -0.67
    throp
    -0.66
    uffs
    -0.66
     Bout
    -0.65
    Preview
    -0.64
    LAN
    -0.64
    gran
    -0.63
    warm
    -0.62
     dialect
    -0.62
     reve
    -0.61
    POSITIVE LOGITS
     liability
    4.07
     liabilities
    2.32
     LIA
    1.66
     responsibility
    1.53
     liable
    1.44
     obligation
    1.38
     indemn
    1.37
     obligations
    1.29
     negligence
    1.29
     culp
    1.26
    Activations Density 0.020%

    No Known Activations