© 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. 6-RES-JB
    11. 11754
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a significant amount or intensity of something

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "a lot" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    perty
    -0.78
    Constructed
    -0.69
    agate
    -0.69
    sburgh
    -0.68
    gary
    -0.68
    heid
    -0.67
    acus
    -0.66
    ufact
    -0.66
    asury
    -0.65
    bury
    -0.65
    POSITIVE LOGITS
     amount
    0.69
     of
    0.69
    tery
    0.67
    ãĥ³
    0.67
     predictable
    0.65
    ãĤ§
    0.62
     different
    0.62
     worse
    0.61
     nicer
    0.60
    picture
    0.60
    Activations Density 0.042%

    No Known Activations