© 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. 16903
    Prev
    Next
    INDEX
    Explanations

    adjectives or adverbs describing a unique or distinctive quality

    oai_token-act-pair · gpt-3.5-turbo

    words that convey uniqueness or distinctiveness

    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
    OTOS
    -0.77
     flaws
    -0.68
     adoption
    -0.67
    quickShipAvailable
    -0.67
     opposition
    -0.66
    Reviewer
    -0.65
     demolition
    -0.65
     conclusions
    -0.64
     substitution
    -0.63
     Onion
    -0.62
    POSITIVE LOGITS
     suited
    0.82
    responsible
    0.78
     narrated
    0.78
     differentiated
    0.75
     tailored
    0.74
     positioned
    0.72
     tuned
    0.72
     situated
    0.71
     trained
    0.71
     consulted
    0.70
    Activations Density 0.018%

    No Known Activations