© 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. 6753
    Prev
    Next
    INDEX
    Explanations

    press releases and related news articles

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the press or media-related terminology

    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
    abama
    -0.68
    vae
    -0.65
     Bram
    -0.64
    ji
    -0.63
    inho
    -0.63
     [|
    -0.62
    oshi
    -0.62
     Judah
    -0.62
     Trayvon
    -0.61
    anie
    -0.61
    POSITIVE LOGITS
    urized
    1.42
    ured
    1.06
    ures
    1.05
     conferences
    1.04
    URE
    0.98
     corps
    0.95
     conference
    0.93
    ur
    0.89
    ure
    0.89
     secretary
    0.89
    Activations Density 0.041%

    No Known Activations