© 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. 22611
    Prev
    Next
    INDEX
    Explanations

    instances of the word "zoom" and related words in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "zoom" or "room."

    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
    ãĤ·ãĥ£
    -0.85
    nces
    -0.82
    uana
    -0.75
     conduc
    -0.71
    idates
    -0.68
    wcsstore
    -0.66
    chnology
    -0.65
    utherland
    -0.65
    ounters
    -0.65
    ivities
    -0.64
    POSITIVE LOGITS
    hower
    1.03
    ooming
    0.97
    oom
    0.94
    orph
    0.93
    ed
    0.82
    edIn
    0.81
     Boom
    0.78
    opot
    0.75
     Kinnikuman
    0.74
    stead
    0.72
    Activations Density 0.034%

    No Known Activations