© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 9277
    Prev
    Next
    INDEX
    Explanations

    terms related to various technical and scientific topics

    oai_token-act-pair · gpt-3.5-turbo

    themes related to narratives and their complexities

    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
    ITNESS
    -0.81
    CLASSIFIED
    -0.67
    amaz
    -0.64
    itant
    -0.59
    ukong
    -0.58
    Fax
    -0.57
    )=
    -0.55
    ificantly
    -0.55
    OND
    -0.54
    essage
    -0.53
    POSITIVE LOGITS
     into
    1.04
     onto
    0.80
     Into
    0.76
    into
    0.75
     thereby
    0.74
     effortlessly
    0.73
     allowing
    0.71
     seamlessly
    0.70
     to
    0.70
     creating
    0.70
    Activations Density 0.604%

    No Known Activations