© 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. 11-RES-JB
    11. 22667
    Prev
    Next
    INDEX
    Explanations

    sentences starting with "Here's."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "Here’s" or variations of it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    soever
    -0.66
    estic
    -0.65
    roit
    -0.61
    æĪ¦
    -0.60
    alties
    -0.60
    okers
    -0.59
    inances
    -0.58
    igr
    -0.57
    children
    -0.56
    ammers
    -0.56
    POSITIVE LOGITS
     hoping
    1.23
     how
    1.19
     why
    1.17
     what
    1.11
     whats
    0.99
     another
    0.96
     WHY
    0.92
     where
    0.90
    how
    0.90
     something
    0.88
    Activations Density 0.036%

    No Known Activations