© 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. 7-RES-JB
    11. 12465
    Prev
    Next
    INDEX
    Explanations

    phrases related to events or actions happening before and after a certain point

    oai_token-act-pair · gpt-3.5-turbo

    connections related to time frames, particularly focusing on events happening before and after specific moments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Petr
    -0.68
    illi
    -0.66
    gur
    -0.66
    ãĤ´
    -0.64
    Merit
    -0.62
     Romeo
    -0.62
     Reson
    -0.61
    natureconservancy
    -0.60
    Dir
    -0.60
    ãĤ©
    -0.59
    POSITIVE LOGITS
    ecycle
    0.72
    etheus
    0.71
    isode
    0.70
    effects
    0.70
    thens
    0.64
    rogen
    0.64
    aucas
    0.64
     acquaint
    0.63
    anwhile
    0.63
    idth
    0.63
    Activations Density 0.103%

    No Known Activations