© 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. 24014
    Prev
    Next
    INDEX
    Explanations

    corporate names

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific media companies and brands

    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
    isers
    -0.72
     reserve
    -0.70
    istically
    -0.65
    ppa
    -0.65
    ocl
    -0.64
    iste
    -0.60
     Archdemon
    -0.60
     Jarrett
    -0.59
     scrimmage
    -0.59
    isms
    -0.59
    POSITIVE LOGITS
    washer
    1.12
    onest
    1.02
    MpServer
    0.99
     Dish
    0.85
    renheit
    0.84
    Eye
    0.81
    bone
    0.76
    mare
    0.76
    izon
    0.75
    XM
    0.74
    Activations Density 0.013%

    No Known Activations