© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 12111
    Prev
    Next
    INDEX
    Explanations

    phrases indicating comparison or similarity

    oai_token-act-pair · gpt-3.5-turbo

    empty text sections or formatting tokens

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MORE
    -0.56
    astern
    -0.53
    ——
    -0.52
     doorstep
    -0.49
    athan
    -0.47
    âĻ¥
    -0.47
     unlaw
    -0.47
     whatsoever
    -0.47
    ALLY
    -0.47
    WAYS
    -0.47
    POSITIVE LOGITS
    ylum
    1.05
    ynchron
    1.03
    ynchronous
    1.01
    ync
    0.97
    bestos
    0.96
    pires
    0.96
    pire
    0.96
    semble
    0.93
    pired
    0.91
    phy
    0.90
    Activations Density 0.066%

    No Known Activations