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. 11-RES-JB
    6. 8952
    Prev
    Next
    INDEX
    Explanations

    phrases indicating attempts to contact or help someone in need

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating attempts or efforts related to coordination and assistance

    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
    hemy
    -0.81
    gling
    -0.73
    Lear
    -0.71
    soType
    -0.70
     Sins
    -0.65
     Invention
    -0.65
    Ranked
    -0.65
     Likes
    -0.64
    )=(
    -0.63
     blasphemy
    -0.63
    POSITIVE LOGITS
     evacuate
    1.68
     reopen
    1.28
     rescue
    1.22
     restore
    1.17
     relocate
    1.16
     recover
    1.16
     disinfect
    1.14
     dispose
    1.14
     apprehend
    1.13
     locate
    1.13
    Activations Density 0.263%

    No Known Activations