© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 5130
    Prev
    Next
    INDEX
    Explanations

    long phrases or sentences describing difficult or challenging tasks or experiences

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating coercive or forced actions

    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
     clinging
    -0.75
    weak
    -0.73
    channelAvailability
    -0.72
    vote
    -0.69
    ndum
    -0.65
    bern
    -0.62
    BUG
    -0.61
     sqor
    -0.61
    eb
    -0.61
    adal
    -0.60
    POSITIVE LOGITS
     involves
    1.81
     involve
    1.53
     culmin
    1.45
     entails
    1.43
     lasts
    1.35
     consisted
    1.33
     involved
    1.30
     consists
    1.27
     lasted
    1.27
     entail
    1.26
    Activations Density 0.452%

    No Known Activations