© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 7-RES-JB
    11. 11697
    Prev
    Next
    INDEX
    Explanations

    words related to obstruction or prevention

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "block" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lli
    -0.74
    mble
    -0.71
     prest
    -0.69
    rious
    -0.67
    gow
    -0.66
    BUS
    -0.66
    llers
    -0.65
    enture
    -0.65
    brates
    -0.64
    brate
    -0.63
    POSITIVE LOGITS
    buster
    1.09
    busters
    1.00
    aded
    0.95
    ades
    0.92
    quote
    0.89
    ading
    0.85
    chains
    0.79
     blocking
    0.79
    picking
    0.76
     blockade
    0.75
    Activations Density 0.037%

    No Known Activations