© 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. 4-RES-JB
    11. 7587
    Prev
    Next
    INDEX
    Explanations

    phrases related to objects used as props in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to props, especially in a cinematic or theatrical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Carbuncle
    -0.86
    soever
    -0.75
    Interstitial
    -0.69
     Maw
    -0.67
     Intent
    -0.67
     MacArthur
    -0.66
     Crimson
    -0.66
    lihood
    -0.64
     Conversation
    -0.64
    clair
    -0.63
    POSITIVE LOGITS
    ulsive
    1.22
    itious
    1.12
    etry
    0.99
     prop
    0.96
    uls
    0.91
    ounded
    0.86
    hetical
    0.86
    onents
    0.85
    ulsion
    0.82
    ylene
    0.81
    Activations Density 0.009%

    No Known Activations