© 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. 11-RES-JB
    11. 1262
    Prev
    Next
    INDEX
    Explanations

    phrases related to human connections and relationships

    oai_token-act-pair · gpt-3.5-turbo

    references to various groups and entities that relate to support systems and clients

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
    WithNo
    -0.60
     Kov
    -0.58
     protester
    -0.58
     unification
    -0.57
     convergence
    -0.57
    otos
    -0.57
     Thing
    -0.56
     itself
    -0.55
     disturbance
    -0.55
    noon
    -0.55
    POSITIVE LOGITS
    '
    1.34
    hip
    1.33
    hips
    1.32
    hare
    1.14
     selves
    1.05
    creen
    1.05
    heet
    1.05
     counterparts
    1.01
    mith
    1.01
    ervative
    1.00
    Activations Density 0.360%

    No Known Activations