© 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. 0-RES-JB
    11. 6395
    Prev
    Next
    INDEX
    Explanations

    keywords related to the "bottom" position or concept

    oai_token-act-pair · gpt-3.5-turbo

    repeated references to the concept of "bottom."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hunt
    -0.81
    adden
    -0.71
    urion
    -0.66
    ians
    -0.65
    ²¾
    -0.65
    ian
    -0.63
    aur
    -0.62
    lessly
    -0.62
    express
    -0.62
    ually
    -0.61
    POSITIVE LOGITS
     bottom
    3.71
    bottom
    2.49
     Bottom
    2.46
    Bottom
    2.23
     top
    1.66
     bott
    1.51
     underside
    1.39
     lowest
    1.26
     Top
    1.25
    top
    1.22
    Activations Density 0.018%

    No Known Activations