© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 10-RES-JB
    11. 1309
    Prev
    Next
    INDEX
    Explanations

    phrases that introduce a new topic or idea

    oai_token-act-pair · gpt-3.5-turbo

    instances of the conjunction "and" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onia
    -0.71
    mite
    -0.71
    orm
    -0.70
    alted
    -0.70
    umper
    -0.68
    VOL
    -0.67
    ãĥł
    -0.66
    ahime
    -0.64
    ãĥ¼ãĥ
    -0.63
    ãĥį
    -0.63
    POSITIVE LOGITS
     how
    1.68
     why
    1.46
     whether
    1.28
    why
    1.20
    how
    1.18
     what
    1.12
     discusses
    1.11
     WHY
    1.06
     HOW
    1.02
     implications
    0.97
    Activations Density 0.296%

    No Known Activations