© 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. 7211
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific term or entity, likely a proper noun starting with "Fl"

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific entity or character associated with the "Fl" identifier

    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
    eers
    -0.89
    terday
    -0.83
    eering
    -0.77
    anwhile
    -0.77
     Learns
    -0.74
     conclud
    -0.69
     Carbuncle
    -0.67
    selves
    -0.66
    EngineDebug
    -0.65
    ItemTracker
    -0.65
    POSITIVE LOGITS
    avour
    1.16
    uffy
    1.15
    iltration
    1.09
    acies
    1.02
    icker
    0.96
    ights
    0.96
    oss
    0.96
    utter
    0.95
    usions
    0.94
    idious
    0.92
    Activations Density 0.010%

    No Known Activations