© 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. 6-RES-JB
    11. 13548
    Prev
    Next
    INDEX
    Explanations

    words related to prevention or obstruction of actions or processes

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to prevention or blockage of actions or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çīĪ
    -0.73
    eria
    -0.70
    clair
    -0.69
     aback
    -0.65
     summar
    -0.65
    xtap
    -0.65
    fortunately
    -0.63
    hooting
    -0.63
     awaits
    -0.63
    etheless
    -0.62
    POSITIVE LOGITS
     anymore
    0.95
    BuyableInstoreAndOnline
    0.87
     altogether
    0.84
     anything
    0.82
     harmful
    0.74
     any
    0.73
     Expend
    0.67
     violent
    0.66
     toxic
    0.65
     undue
    0.65
    Activations Density 0.153%

    No Known Activations