© 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. 0-RES-JB
    11. 19966
    Prev
    Next
    INDEX
    Explanations

    acronyms starting with "AS."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the acronym "AS" in various contexts

    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
     sums
    -0.72
     Wallace
    -0.69
     purse
    -0.65
     quo
    -0.61
     fences
    -0.61
     persu
    -0.61
     laborers
    -0.61
     Monk
    -0.60
    pired
    -0.60
     foul
    -0.60
    POSITIVE LOGITS
    AS
    3.82
    ASE
    1.91
    ASED
    1.80
    AST
    1.80
    ASC
    1.69
     AS
    1.59
    ANS
    1.52
    AT
    1.51
    ADS
    1.51
    AF
    1.48
    Activations Density 0.015%

    No Known Activations