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. 7-RES-JB
    6. 20204
    Prev
    Next
    INDEX
    Explanations

    References to actions or events that occurred or may occur

    oai_token-act-pair · gpt-3.5-turbo

    sentences that convey opinions or statements regarding legal matters and commentary

    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
    QB
    -0.81
    çľ
    -0.71
     Ãľ
    -0.68
    Border
    -0.67
    é¾
    -0.66
    äºĶ
    -0.66
    Unit
    -0.63
    ãĥĩ
    -0.63
    Nation
    -0.61
    ãĥĺ
    -0.60
    POSITIVE LOGITS
     nevertheless
    1.44
     nonetheless
    1.36
     anecd
    1.04
     occasionally
    0.74
     anyway
    0.74
    efficients
    0.73
     theoretically
    0.70
     occasional
    0.69
     anyways
    0.69
    lear
    0.68
    Activations Density 0.708%

    No Known Activations