© 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. 4-RES-JB
    11. 7138
    Prev
    Next
    INDEX
    Explanations

    keywords denoting uncertainty or open possibilities

    oai_token-act-pair · gpt-3.5-turbo

    the indefinite pronoun "any."

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

    No Comments

    Negative Logits
    rex
    -0.76
    rez
    -0.69
     Alps
    -0.66
     Trib
    -0.64
    pees
    -0.61
    lymp
    -0.60
    romy
    -0.58
    bows
    -0.58
    staking
    -0.57
    DA
    -0.57
    POSITIVE LOGITS
    THING
    1.29
    body
    1.23
    where
    1.22
    WHERE
    0.98
    how
    0.84
    etheless
    0.78
    ways
    0.77
    thin
    0.76
    ONE
    0.76
     conceivable
    0.74
    Activations Density 0.049%

    No Known Activations