© 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. 9723
    Prev
    Next
    INDEX
    Explanations

    keywords related to administrative or organizational backlogs

    oai_token-act-pair · gpt-3.5-turbo

    references to infrastructure issues and public safety events

    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
    oking
    -0.76
    orb
    -0.75
    uters
    -0.75
    oline
    -0.74
    auri
    -0.73
    apor
    -0.72
    eely
    -0.70
    ater
    -0.69
    hap
    -0.69
    obar
    -0.68
    POSITIVE LOGITS
    ged
    0.99
     backlog
    0.95
    ewater
    0.85
    ging
    0.76
    gments
    0.74
     Laden
    0.74
    clud
    0.73
    gone
    0.69
    gement
    0.69
     STOR
    0.68
    Activations Density 0.028%

    No Known Activations