© 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. 3-RES-JB
    11. 10814
    Prev
    Next
    INDEX
    Explanations

    names involving a mix of upper and lower case letters

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, likely names of people or places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    taboola
    -1.06
    BILITIES
    -0.82
    ioxide
    -0.81
     Cosponsors
    -0.80
    Cola
    -0.72
     Expend
    -0.70
    Cause
    -0.68
     guiActiveUnfocused
    -0.67
    invoke
    -0.66
    ãĥīãĥ©ãĤ´ãĥ³
    -0.66
    POSITIVE LOGITS
    inki
    0.95
    wed
    0.90
    zik
    0.81
    idan
    0.81
    iday
    0.80
    quarters
    0.75
    igans
    0.73
    ournals
    0.71
    acan
    0.71
    sworth
    0.71
    Activations Density 0.301%

    No Known Activations