© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 12-RES-JB
    11. 3031
    Prev
    Next
    INDEX
    Explanations

    information related to research funding and political positions on evidence-based policy making

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    relationships between causes and effects in various issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    reet
    -0.84
    Dialogue
    -0.81
    estyles
    -0.73
    Vis
    -0.73
    lance
    -0.72
    istered
    -0.71
    phabet
    -0.70
    owship
    -0.68
     Dialogue
    -0.68
    aram
    -0.68
    POSITIVE LOGITS
     causes
    1.64
     culprit
    1.63
     cause
    1.61
     causation
    1.58
     explanation
    1.53
     motive
    1.50
     explanations
    1.48
    cause
    1.46
     caus
    1.46
     contribut
    1.45
    Activations Density 0.391%

    No Known Activations