Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 9949
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "look at"

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "look at" in various contexts, indicating a focus on examination or analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    widget
    -0.71
    NL
    -0.66
    trap
    -0.66
     engineered
    -0.65
     campaigner
    -0.62
    TN
    -0.62
    bestos
    -0.62
     benefited
    -0.59
    bender
    -0.59
    cell
    -0.58
    POSITIVE LOGITS
     least
    0.89
    ĸļ
    0.84
    =-=-=-=-
    0.80
    mosp
    0.78
    ļéĨĴ
    0.77
     halftime
    0.76
     Replay
    0.72
     angles
    0.72
    olphins
    0.70
    rical
    0.70
    Activations Density 0.082%

    No Known Activations