© 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. 10414
    Prev
    Next
    INDEX
    Explanations

    the names of organizations or institutions

    oai_token-act-pair · gpt-3.5-turbo

    elements of organizations or institutions mentioned in a context

    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
     symptoms
    -0.78
     hump
    -0.71
     trouble
    -0.71
     visions
    -0.70
     dreams
    -0.67
     turbines
    -0.66
     essentials
    -0.65
     iceberg
    -0.64
     symptom
    -0.62
    worldly
    -0.62
    POSITIVE LOGITS
     Ala
    0.84
    Gall
    0.81
     Leban
    0.81
     Ltd
    0.79
     aka
    0.79
     excluding
    0.74
    76561
    0.74
     including
    0.74
     Calif
    0.73
     etc
    0.72
    Activations Density 0.470%

    No Known Activations