© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 11-RES-JB
    11. 22340
    Prev
    Next
    INDEX
    Explanations

    technical terms related to technology and testing

    oai_token-act-pair · gpt-3.5-turbo

    mentions of tests or assessments in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SPONSORED
    -0.78
    billion
    -0.77
    Ó
    -0.70
    winning
    -0.68
    this
    -0.67
    these
    -0.67
    nothing
    -0.66
     exactly
    -0.66
    the
    -0.65
    á¸
    -0.64
    POSITIVE LOGITS
     Miscellaneous
    0.81
     secondary
    0.73
     supplementary
    0.71
     standby
    0.70
     Secondary
    0.70
     supplemental
    0.68
     auxiliary
    0.68
     thermal
    0.64
     intra
    0.63
     newcom
    0.63
    Activations Density 0.813%

    No Known Activations