© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1-RES-JB
    11. 24069
    Prev
    Next
    INDEX
    Explanations

    phrases related to adhesive materials

    oai_token-act-pair · gpt-3.5-turbo

    terms related to bonding and adhesive substances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    akening
    -0.77
    OUN
    -0.76
    artment
    -0.75
    nen
    -0.75
    nn
    -0.72
    inen
    -0.72
    oulos
    -0.72
    ounces
    -0.71
    erenn
    -0.71
    vana
    -0.70
    POSITIVE LOGITS
     glue
    1.38
     adhesive
    0.97
     solvent
    0.93
     solder
    0.91
     plaster
    0.90
     resin
    0.89
    driver
    0.88
    eer
    0.85
     residue
    0.82
     bonded
    0.80
    Activations Density 0.018%

    No Known Activations