© 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. 17493
    Prev
    Next
    INDEX
    Explanations

    verbs and nouns related to the action of obstructing or preventing something

    oai_token-act-pair · gpt-3.5-turbo

    instances of blocking or obstructing actions or events

    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
    olate
    -0.72
    orically
    -0.69
    xual
    -0.68
    emic
    -0.68
    algia
    -0.66
    mia
    -0.64
     Volunte
    -0.64
    lli
    -0.63
    elt
    -0.63
     warmed
    -0.62
    POSITIVE LOGITS
     access
    1.08
    aded
    0.87
    ades
    0.87
    buster
    0.84
     entrance
    0.82
    ading
    0.77
     entry
    0.75
     accessing
    0.75
    quote
    0.74
     entrances
    0.74
    Activations Density 0.045%

    No Known Activations