© 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. 10-RES-JB
    11. 17384
    Prev
    Next
    INDEX
    Explanations

    mentions of quantities or numbers over a certain threshold

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating large quantities or numbers

    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
    ffen
    -0.66
     breeze
    -0.63
    ":[
    -0.55
     doom
    -0.55
    ELY
    -0.54
     Slug
    -0.54
    ittal
    -0.54
     onward
    -0.53
     Dynamics
    -0.53
    ãĤº
    -0.52
    POSITIVE LOGITS
     9000
    1.20
    drive
    1.16
    capacity
    1.15
    grown
    1.15
    kill
    1.14
    population
    1.11
    priced
    1.11
    loading
    1.10
    whelming
    1.10
    tones
    1.09
    Activations Density 0.050%

    No Known Activations