© 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. 8-RES-JB
    11. 7029
    Prev
    Next
    INDEX
    Explanations

    instances of the word "identify" or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the act of identification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fare
    -0.80
    ework
    -0.72
    orld
    -0.70
     acquitted
    -0.64
    obar
    -0.63
     besie
    -0.63
    steel
    -0.62
    icum
    -0.62
    hetti
    -0.61
     reeling
    -0.61
    POSITIVE LOGITS
     weaknesses
    0.82
     flaws
    0.81
    ively
    0.79
    pointers
    0.77
     shortcomings
    0.74
     landmarks
    0.73
    idable
    0.71
     gaps
    0.70
     deficiencies
    0.70
     faults
    0.69
    Activations Density 0.055%

    No Known Activations