© 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. 8-RES-JB
    11. 6903
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a large number of people showing interest, involvement, or shared experience in a context

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "have"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Anyway
    -0.65
     Apart
    -0.62
    most
    -0.61
    vi
    -0.59
    anny
    -0.57
     Niet
    -0.56
    NOR
    -0.56
    TG
    -0.56
    advertising
    -0.55
     Pair
    -0.55
    POSITIVE LOGITS
     been
    1.43
    been
    1.29
     gotten
    1.14
     undergone
    1.12
     gone
    1.10
     fallen
    1.09
     arisen
    1.03
     risen
    1.01
     Been
    1.00
     come
    0.97
    Activations Density 0.195%

    No Known Activations