© 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. 10-RES-JB
    11. 16459
    Prev
    Next
    INDEX
    Explanations

    verbs related to the description or representation of something or someone

    oai_token-act-pair · gpt-3.5-turbo

    various forms of the word "portray" and its derivatives in the context of representations and depictions of individuals or themes

    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
    kson
    -0.64
    sterdam
    -0.63
    iqueness
    -0.63
    scrib
    -0.62
    foreseen
    -0.62
     drawer
    -0.62
    kers
    -0.61
    won
    -0.60
     confir
    -0.60
    ni
    -0.59
    POSITIVE LOGITS
     portray
    1.34
     depictions
    1.21
     portrayal
    1.17
     portraying
    1.11
     portrays
    1.05
     depiction
    1.04
     depict
    0.98
     portrayed
    0.98
     depicting
    0.98
     depicts
    0.95
    Activations Density 0.092%

    No Known Activations