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. 10-RES-JB
    6. 7581
    Prev
    Next
    INDEX
    Explanations

    phrases related to reasonable or logical thinking

    oai_token-act-pair · gpt-3.5-turbo

    references to rationality or common sense in discussions about people and their behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Reloaded
    -0.69
     Anniversary
    -0.66
     disappearance
    -0.65
     Regions
    -0.62
     Territories
    -0.61
     Promise
    -0.60
    apeake
    -0.60
     Siege
    -0.60
     rehearsal
    -0.59
    forestation
    -0.59
    POSITIVE LOGITS
     inclined
    0.85
    think
    0.83
    kie
    0.80
    ellectual
    0.80
    thinking
    0.79
    tarian
    0.78
    iuses
    0.78
    ascript
    0.77
     instinctively
    0.77
    enance
    0.77
    Activations Density 0.377%

    No Known Activations