© 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. 0-RES-JB
    11. 2154
    Prev
    Next
    INDEX
    Explanations

    adjectives associated with describing specific traits or features

    oai_token-act-pair · gpt-3.5-turbo

    terms related to characteristics or qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eworks
    -0.78
     FML
    -0.76
    udget
    -0.72
    fill
    -0.71
    pay
    -0.71
    Deal
    -0.67
    ebin
    -0.67
    ravel
    -0.67
     PAY
    -0.66
    aneously
    -0.65
    POSITIVE LOGITS
     characteristic
    3.39
     distinctive
    2.49
     distinguishing
    1.63
     hallmark
    1.56
     peculiar
    1.49
     trademark
    1.42
     customary
    1.31
     unmist
    1.26
     characteristics
    1.23
     expressive
    1.20
    Activations Density 0.037%

    No Known Activations