© 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. 6230
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific entities or characters, particularly ones followed by a title or epithet

    oai_token-act-pair · gpt-3.5-turbo

    terms related to stars and their representation in media and literature

    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
    afety
    -0.85
    azard
    -0.69
    anmar
    -0.68
    channelAvailability
    -0.68
     upkeep
    -0.64
    FINEST
    -0.64
    ashtra
    -0.64
     nets
    -0.63
     rudimentary
    -0.60
     CTR
    -0.59
    POSITIVE LOGITS
    ciating
    0.78
     Poker
    0.78
     Leia
    0.75
     Gleaming
    0.73
    Irish
    0.73
     Females
    0.73
     Awakens
    0.70
     Planetary
    0.67
    ¥µ
    0.66
    otos
    0.65
    Activations Density 0.145%

    No Known Activations