© 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. 8537
    Prev
    Next
    INDEX
    Explanations

    prepositions and conjunctions indicating relationships between entities

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate comparisons or contrasts between entities or concepts

    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
    NetMessage
    -0.36
    ĵĺ
    -0.30
    natureconservancy
    -0.30
     Mages
    -0.29
    BUG
    -0.29
     WATCHED
    -0.29
     Pwr
    -0.29
     cryst
    -0.29
    catentry
    -0.28
    Ĥª
    -0.28
    POSITIVE LOGITS
    ividual
    0.45
    lycer
    0.34
    ictionary
    0.34
    uart
    0.33
    idth
    0.33
    aghd
    0.31
    allery
    0.31
    hower
    0.30
    okane
    0.30
    iazep
    0.30
    Activations Density 3.499%

    No Known Activations