© 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. 3-RES-JB
    11. 9122
    Prev
    Next
    INDEX
    Explanations

    adjectives and verbs related to effort and action

    oai_token-act-pair · gpt-3.5-turbo

    expressions of action or movement related to planning and preparation

    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
    orsi
    -0.74
     Citation
    -0.69
     flown
    -0.65
     referring
    -0.62
     telling
    -0.61
     thanking
    -0.61
     Fowler
    -0.60
     disclosing
    -0.60
     demonstrating
    -0.59
     1983
    -0.58
    POSITIVE LOGITS
    ãĥīãĥ©
    0.79
    ictionary
    0.79
    thood
    0.74
    hetics
    0.73
    thin
    0.73
    endas
    0.73
    =-=-=-=-=-=-=-=-
    0.69
    unks
    0.66
     VIDEOS
    0.65
    ãĤ¼
    0.65
    Activations Density 2.036%

    No Known Activations