© 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. 0-RES-JB
    11. 2745
    Prev
    Next
    INDEX
    Explanations

    instances of the word "consistent" in texts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "consistent" in various contexts

    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
    iere
    -0.68
    ury
    -0.67
    Enter
    -0.67
     airs
    -0.66
    yang
    -0.66
    hello
    -0.64
    gate
    -0.63
    mare
    -0.62
    ode
    -0.61
    turned
    -0.61
    POSITIVE LOGITS
     consistent
    3.52
     inconsistent
    2.32
     consistency
    1.92
     consistently
    1.73
     predictable
    1.39
     coherent
    1.37
     reliable
    1.35
     satisfactory
    1.34
     inconsistency
    1.32
     inconsist
    1.30
    Activations Density 0.009%

    No Known Activations