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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8-RES-JB
    11. 4028
    Prev
    Next
    INDEX
    Explanations

    specific locations or objects

    oai_token-act-pair · gpt-3.5-turbo

    nouns related to places and organizational contexts

    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
    aughs
    -0.60
    \\\\\\\\\\\\\\\\
    -0.59
    agonist
    -0.59
    Thumbnail
    -0.58
    BUG
    -0.58
    icter
    -0.58
    maxwell
    -0.56
    rification
    -0.56
     logo
    -0.55
    ongevity
    -0.55
    POSITIVE LOGITS
    hops
    1.23
    paces
    1.22
    chool
    1.18
    hips
    1.13
    heet
    1.09
    mith
    1.05
    poons
    1.02
    hare
    1.01
    hots
    1.00
    pace
    0.99
    Activations Density 0.358%

    No Known Activations