© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 1096
    Prev
    Next
    INDEX
    Explanations

    references to data input in a technical context

    oai_token-act-pair · gpt-3.5-turbo

    references to input and output in data processing contexts

    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
     Nguyen
    -0.84
    llan
    -0.74
    astern
    -0.71
     Mub
    -0.66
     Peninsula
    -0.62
     Reincarn
    -0.62
     sunset
    -0.62
     Colon
    -0.62
     Willis
    -0.61
    ethe
    -0.60
    POSITIVE LOGITS
    ting
    1.49
    ted
    1.48
    ters
    1.09
    TING
    0.88
    raw
    0.84
     impedance
    0.82
    Stream
    0.80
    ories
    0.80
    Iterator
    0.78
    ible
    0.78
    Activations Density 0.044%

    No Known Activations