© 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. 9276
    Prev
    Next
    INDEX
    Explanations

    terms related to politics and policies

    oai_token-act-pair · gpt-3.5-turbo

    terms related to political issues and social matters

    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
    asca
    -0.57
    ļéĨĴ
    -0.56
    senal
    -0.54
    Balt
    -0.52
     gulf
    -0.50
     alike
    -0.50
    ä¿
    -0.50
    Ĩ
    -0.50
    othermal
    -0.49
    Anth
    -0.49
    POSITIVE LOGITS
     &
    1.07
    and
    1.04
     and
    1.03
     AND
    1.01
    &
    0.97
    /
    0.93
     or
    0.85
    /+
    0.85
    /
    0.81
     +
    0.80
    Activations Density 0.576%

    No Known Activations