© 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. 10-RES-JB
    11. 10471
    Prev
    Next
    INDEX
    Explanations

    instances where something is being done or happening because of a specific reason

    oai_token-act-pair · gpt-3.5-turbo

    the causal relationships expressed through the word "because."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    joined
    -0.72
    foundland
    -0.70
     exting
    -0.68
    aug
    -0.68
     pione
    -0.67
    scribe
    -0.66
    ilet
    -0.66
    ãĤ©
    -0.64
    mint
    -0.64
    aiden
    -0.64
    POSITIVE LOGITS
     they
    1.14
     of
    1.12
     thereof
    0.94
     there
    0.94
     it
    0.92
     THEY
    0.89
     he
    0.85
     nobody
    0.85
     OF
    0.82
    of
    0.81
    Activations Density 0.093%

    No Known Activations