© 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. 18549
    Prev
    Next
    INDEX
    Explanations

    phrases related to prevention or obstruction

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating prohibition or prevention

    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
    aic
    -0.72
    ector
    -0.70
    rote
    -0.69
    wait
    -0.68
    elman
    -0.66
    arse
    -0.66
    abre
    -0.66
    olitical
    -0.64
    ety
    -0.63
    lyak
    -0.63
    POSITIVE LOGITS
     accessing
    1.50
     entering
    1.40
     reaching
    1.38
     harming
    1.38
     obtaining
    1.35
     interfering
    1.34
     achieving
    1.31
     completing
    1.30
     joining
    1.30
     gaining
    1.29
    Activations Density 0.068%

    No Known Activations