© 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. 10-RES-JB
    6. 1444
    Prev
    Next
    INDEX
    Explanations

    instances where responses or feedback have not been received

    oai_token-act-pair · gpt-3.5-turbo

    instances of denial or rejection in a narrative context

    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
    emies
    -0.69
     incorrectly
    -0.68
    ometimes
    -0.66
    tein
    -0.66
     disadvantages
    -0.63
     underestimated
    -0.62
    Downloadha
    -0.60
     misconception
    -0.60
     unintentionally
    -0.60
     Sins
    -0.60
    POSITIVE LOGITS
     forthcoming
    1.02
     bud
    1.00
     avail
    0.93
     satisfactory
    0.88
     reply
    0.80
     muster
    0.75
    Response
    0.75
     replied
    0.75
     fruition
    0.75
     completion
    0.75
    Activations Density 0.314%

    No Known Activations