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. 11-RES-JB
    6. 15561
    Prev
    Next
    INDEX
    Explanations

    mentions of legal and criminal activities or events

    oai_token-act-pair · gpt-3.5-turbo

    phrases and terms related to legal penalties and incarceration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    his
    -0.61
    wered
    -0.60
    "))
    -0.57
     proble
    -0.57
     HIS
    -0.52
     Its
    -0.52
    atcher
    -0.51
     its
    -0.51
    alon
    -0.51
     his
    -0.50
    POSITIVE LOGITS
     respectively
    2.14
     apiece
    1.63
     together
    1.60
    together
    1.32
     jointly
    1.30
     collectively
    1.28
     themselves
    1.23
     respective
    1.22
    selves
    1.20
     Together
    1.17
    Activations Density 0.930%

    No Known Activations