© 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. 6572
    Prev
    Next
    INDEX
    Explanations

    words related to conducting tests or experiments

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to experimentation or testing processes

    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
    brance
    -0.78
    lance
    -0.76
    iture
    -0.73
    atra
    -0.70
    itures
    -0.69
    MpServer
    -0.68
    CENT
    -0.67
    atto
    -0.67
    taboola
    -0.66
    vation
    -0.65
    POSITIVE LOGITS
     hypotheses
    1.20
     whether
    1.09
    osterone
    0.91
     feasibility
    0.88
     hypothesis
    0.87
     authenticity
    0.79
     theories
    0.79
    whether
    0.78
     viability
    0.78
    orously
    0.73
    Activations Density 0.100%

    No Known Activations