© 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. 12414
    Prev
    Next
    INDEX
    Explanations

    phrases indicating causation

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate causation or consequence

    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
    nets
    -0.71
    isable
    -0.69
    arge
    -0.68
    ensical
    -0.66
     pse
    -0.62
    ccording
    -0.61
    gee
    -0.60
    ©¶æ¥µ
    -0.60
    ribes
    -0.60
    front
    -0.59
    POSITIVE LOGITS
     sheer
    0.84
     course
    0.76
    âĶĢâĶĢâĶĢâĶĢ
    0.72
     precaution
    0.69
     their
    0.64
     inexper
    0.64
     luck
    0.64
     sudden
    0.60
     exhaustion
    0.59
    VERTIS
    0.59
    Activations Density 0.070%

    No Known Activations