© 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. 4-RES-JB
    11. 7479
    Prev
    Next
    INDEX
    Explanations

    connections between events or situations and the act of assigning blame or responsibility

    oai_token-act-pair · gpt-3.5-turbo

    phrases that denote blame or attribution

    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
    ecast
    -0.75
    alde
    -0.71
    adia
    -0.71
    ibaba
    -0.68
    DH
    -0.67
     workplaces
    -0.65
    MW
    -0.65
     floors
    -0.65
    cludes
    -0.65
    rentices
    -0.62
    POSITIVE LOGITS
     blame
    0.80
    à¨
    0.76
    Ö¼
    0.69
     culprit
    0.68
     Allaah
    0.68
     bluff
    0.68
    ãĤ§
    0.67
     acronym
    0.67
    è¦ļéĨĴ
    0.66
    ̶
    0.64
    Activations Density 0.133%

    No Known Activations