© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 16615
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "human" in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to human characteristics and attributes

    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
    ãĥ´ãĤ¡
    -0.82
    terness
    -0.75
    RAG
    -0.71
    é¾įå
    -0.70
    forth
    -0.69
    arity
    -0.69
     Franch
    -0.68
    raise
    -0.67
    åĭ
    -0.65
    bg
    -0.65
    POSITIVE LOGITS
    oids
    1.22
     beings
    1.17
     readable
    0.98
    oid
    0.92
    zee
    0.88
    made
    0.87
     embryonic
    0.79
     traffickers
    0.76
     colonists
    0.76
     genome
    0.75
    Activations Density 0.036%

    No Known Activations