© 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. 0-RES-JB
    11. 13787
    Prev
    Next
    INDEX
    Explanations

    specific sequences of two uppercase letters followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    references to the acronym "AS" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kered
    -0.79
    leground
    -0.76
    pill
    -0.68
    opal
    -0.68
    emetery
    -0.67
    moon
    -0.63
    rib
    -0.63
    Cube
    -0.63
    omer
    -0.62
    eming
    -0.62
    POSITIVE LOGITS
     AS
    3.57
    AS
    1.75
     ASA
    1.49
     ASD
    1.45
     ASC
    1.43
     AN
    1.43
     AT
    1.40
     AST
    1.38
     AB
    1.38
     UA
    1.37
    Activations Density 0.014%

    No Known Activations