© 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. 17402
    Prev
    Next
    INDEX
    Explanations

    references to residential homes and housing-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to home ownership and real estate

    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
    uality
    -0.76
    REDACTED
    -0.66
     Archdemon
    -0.66
     rider
    -0.65
     Delta
    -0.64
    xon
    -0.63
    ĸļ
    -0.63
    DragonMagazine
    -0.63
     Slaughter
    -0.62
     paralysis
    -0.62
    POSITIVE LOGITS
    chool
    1.55
    pun
    1.23
    builder
    1.12
    buy
    1.12
    building
    1.10
    builders
    1.03
    owners
    0.98
    wives
    0.96
    owner
    0.96
    mort
    0.95
    Activations Density 0.068%

    No Known Activations