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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 4-RES-JB
    6. 14775
    Prev
    Next
    INDEX
    Explanations

    phrases related to the act of checking or verification

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "check" and its variations

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

    No Comments

    Negative Logits
    Church
    -0.73
     Hots
    -0.73
    é¾į
    -0.71
    brance
    -0.67
    BLE
    -0.66
    ãĥĢ
    -0.65
    LOD
    -0.65
    asus
    -0.64
    chal
    -0.64
    nom
    -0.64
    POSITIVE LOGITS
    etts
    0.91
    ysis
    0.87
    lists
    0.82
    boxes
    0.76
    ipers
    0.75
    ers
    0.74
    arded
    0.73
    mate
    0.72
     boxes
    0.71
     check
    0.70
    Activations Density 0.018%

    No Known Activations