© 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. 10-RES-JB
    11. 6601
    Prev
    Next
    INDEX
    Explanations

    expressions related to knowing or understanding a situation or task

    oai_token-act-pair · gpt-3.5-turbo

    phrases regarding individuals' awareness or competence in their actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vig
    -0.73
     somew
    -0.67
     Awareness
    -0.66
     Seasons
    -0.62
     conceivable
    -0.60
     anytime
    -0.59
     awareness
    -0.58
     unavailable
    -0.58
     Vish
    -0.58
    mony
    -0.58
    POSITIVE LOGITS
    ribe
    0.84
    sbm
    0.80
    talking
    0.76
     talking
    0.73
    doing
    0.72
     signing
    0.71
    addle
    0.70
    fw
    0.69
    /$
    0.69
    UCK
    0.69
    Activations Density 0.078%

    No Known Activations