© 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. 14100
    Prev
    Next
    INDEX
    Explanations

    words related to the acronym "AA"

    oai_token-act-pair · gpt-3.5-turbo

    references to academic or credit ratings and sports leagues

    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
    osuke
    -0.78
    iform
    -0.76
    ified
    -0.70
    liness
    -0.67
    eous
    -0.65
    cept
    -0.63
    ographs
    -0.63
     Olymp
    -0.63
     Jenner
    -0.62
    ificate
    -0.62
    POSITIVE LOGITS
     AA
    0.91
    gdala
    0.81
    HHHH
    0.81
    UG
    0.80
    ECA
    0.79
     resil
    0.76
     practition
    0.76
     mosqu
    0.75
    BA
    0.75
    IU
    0.75
    Activations Density 0.007%

    No Known Activations