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

    Neuronpedia

    Jacobian LensNEW
    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. 2-RES-JB
    11. 503
    Prev
    Next
    INDEX
    Explanations

    the word "block" regardless of context

    oai_token-act-pair · gpt-4-turbo

    blocks and unblocks related to various activities or technologies

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "block" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     reluct
    -0.67
    mble
    -0.66
    gencies
    -0.65
    rouse
    -0.64
     semester
    -0.63
     UM
    -0.63
     swear
    -0.62
     Bie
    -0.62
    ournal
    -0.61
    kers
    -0.60
    POSITIVE LOGITS
    buster
    1.18
    busters
    1.03
    block
    0.94
    chain
    0.93
    quote
    0.93
    blocks
    0.84
    chains
    0.84
    ers
    0.82
    iques
    0.81
    aby
    0.78
    Activations Density 0.011%

    No Known Activations