© 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. 1-RES-JB
    11. 20088
    Prev
    Next
    INDEX
    Explanations

    abbreviations or acronyms ending in 'ST'

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the abbreviation "ST" related to specified contexts or functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    metry
    -0.83
    merce
    -0.74
    hound
    -0.74
    metic
    -0.70
    pher
    -0.70
    mits
    -0.67
    metics
    -0.67
    é¾įåĸļ士
    -0.65
    umen
    -0.64
    ptin
    -0.63
    POSITIVE LOGITS
    UFF
    1.07
    REAM
    1.04
    AND
    1.02
    ART
    1.02
    ACK
    1.02
    ST
    0.99
    OCK
    0.96
    ALK
    0.96
    DERR
    0.96
    AGE
    0.92
    Activations Density 0.004%

    No Known Activations