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. 9390
    Prev
    Next
    INDEX
    Explanations

    phrases related to complex or demanding requirements, tasks, or conditions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that denote a necessity or requirement for effort, skill, or resources

    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
    alde
    -0.88
    emies
    -0.73
     Gleaming
    -0.70
    apor
    -0.66
    azar
    -0.66
    20439
    -0.66
    agate
    -0.65
    lane
    -0.65
    Ń·
    -0.65
    alf
    -0.64
    POSITIVE LOGITS
     approval
    0.98
     permission
    0.94
     upfront
    0.93
     modification
    0.92
     intervention
    0.89
     careful
    0.88
     dexterity
    0.86
     patience
    0.85
     upkeep
    0.84
     diligence
    0.82
    Activations Density 0.250%

    No Known Activations