© 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. 4-RES-JB
    11. 10076
    Prev
    Next
    INDEX
    Explanations

    mentions or descriptions of diaries

    oai_token-act-pair · gpt-3.5-turbo

    references to diaries and personal accounts, particularly in the context of war

    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
    inence
    -0.70
    maxwell
    -0.69
    represented
    -0.68
    apply
    -0.68
    AFTA
    -0.67
    ayn
    -0.66
    neutral
    -0.65
    FFFF
    -0.65
    hens
    -0.65
    OPA
    -0.65
    POSITIVE LOGITS
     diary
    1.02
     Diary
    0.91
     entries
    0.90
     journal
    0.85
     Pages
    0.80
     notebook
    0.79
     notebooks
    0.77
     Entry
    0.73
     journals
    0.72
     archives
    0.69
    Activations Density 0.021%

    No Known Activations