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. 23473
    Prev
    Next
    INDEX
    Explanations

    dualities involving top and bottom regions or positions

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and prepositions related to spatial orientations and connections

    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
    76561
    -0.79
     Logged
    -0.77
    recogn
    -0.70
    Time
    -0.69
    readable
    -0.64
    pell
    -0.64
    Registered
    -0.63
    TIME
    -0.61
    orous
    -0.61
    Journal
    -0.61
    POSITIVE LOGITS
     bottom
    1.68
     underside
    1.60
     sides
    1.56
    bottom
    1.43
     rear
    1.37
     Bottom
    1.35
     side
    1.32
     corners
    1.31
    Bottom
    1.29
     middle
    1.27
    Activations Density 0.149%

    No Known Activations