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. 15950
    Prev
    Next
    INDEX
    Explanations

    phrases describing the behavior or characteristics of animals

    oai_token-act-pair · gpt-3.5-turbo

    possessive pronouns referring to animals or their characteristics

    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
    esson
    -0.86
    ruary
    -0.84
    deals
    -0.78
    andy
    -0.75
     Cancel
    -0.73
    isSpecialOrderable
    -0.72
    WP
    -0.69
    roman
    -0.69
    endale
    -0.69
     Logged
    -0.68
    POSITIVE LOGITS
     habitat
    1.42
     claws
    1.32
     jaws
    1.32
     habitats
    1.31
     fins
    1.30
     nests
    1.29
     tails
    1.28
     paws
    1.26
     feathers
    1.23
     dorsal
    1.23
    Activations Density 0.183%

    No Known Activations