© 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. 6470
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific actions or outcomes

    oai_token-act-pair · gpt-3.5-turbo

    modal verbs and their variations that imply necessity or ability

    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
    PDATE
    -0.66
    ross
    -0.66
    prof
    -0.65
     Spectre
    -0.65
    select
    -0.63
    fixes
    -0.62
    asses
    -0.59
    orders
    -0.58
     Dixon
    -0.58
    phase
    -0.58
    POSITIVE LOGITS
     be
    1.55
     BE
    1.24
    Be
    1.17
    be
    1.14
     Be
    1.14
    BE
    1.12
     being
    1.01
     been
    1.01
    being
    0.92
     Being
    0.91
    Activations Density 0.114%

    No Known Activations