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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 5-RES-JB
    6. 21279
    Prev
    Next
    INDEX
    Explanations

    phrases related to final judgments or summaries

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "the bottom line."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    thouse
    -0.82
    sure
    -0.74
    asca
    -0.74
    Äĩ
    -0.74
    agine
    -0.68
    issance
    -0.67
    encers
    -0.66
    apo
    -0.66
    encer
    -0.65
    mun
    -0.64
    POSITIVE LOGITS
     drawer
    0.89
    bottom
    0.86
    most
    0.81
    Bottom
    0.81
    beard
    0.81
    lander
    0.79
    hand
    0.79
     bracket
    0.78
     shelf
    0.78
    lined
    0.75
    Activations Density 0.014%

    No Known Activations