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. 8-RES-JB
    6. 5695
    Prev
    Next
    INDEX
    Explanations

    questions or statements indicating a need for action or resolution

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate necessity or requirement for action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gdala
    -0.72
     Zip
    -0.65
     Democr
    -0.64
     Rost
    -0.62
    izon
    -0.62
     Mamm
    -0.61
     Guilty
    -0.59
     Varg
    -0.57
    theless
    -0.56
    ulty
    -0.56
    POSITIVE LOGITS
     attention
    0.94
    lessly
    0.91
     scrutiny
    0.82
    FINE
    0.77
     tweaking
    0.77
    ENTION
    0.75
     updating
    0.75
     Citation
    0.73
     correction
    0.72
     refinement
    0.72
    Activations Density 0.078%

    No Known Activations