© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 13619
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions or events taking place

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of actions or events that are formally recognized or initiated

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

    No Comments

    Negative Logits
    umbn
    -0.74
    edge
    -0.67
    break
    -0.67
    eno
    -0.66
    cess
    -0.60
    ymph
    -0.60
    enos
    -0.60
    awar
    -0.60
    angan
    -0.59
    upp
    -0.59
    POSITIVE LOGITS
     srf
    0.71
    ãĤ¤ãĥĪ
    0.70
     BY
    0.66
    ¥ŀ
    0.65
     adolesc
    0.62
     aback
    0.62
    netflix
    0.61
    actionDate
    0.60
     hereby
    0.59
     Palestin
    0.59
    Activations Density 0.269%

    No Known Activations