© 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. 11-RES-JB
    11. 20576
    Prev
    Next
    INDEX
    Explanations

    references to the strength or intensity of different aspects

    oai_token-act-pair · gpt-3.5-turbo

    the repeated emphasis on the term "the" in various contexts, indicating a focus on central themes or subjects in discussions

    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
    icia
    -0.84
    lance
    -0.84
    imity
    -0.81
    erity
    -0.81
    gob
    -0.78
    fficiency
    -0.76
    fulness
    -0.76
    worth
    -0.76
    earance
    -0.76
    frog
    -0.75
    POSITIVE LOGITS
     situation
    0.94
     profession
    0.93
     relationship
    0.92
     cosmos
    0.92
     universe
    0.91
     equation
    0.88
     underlying
    0.86
     respective
    0.83
     corpus
    0.82
     environment
    0.81
    Activations Density 0.240%

    No Known Activations