© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RES-JB
    11. 12664
    Prev
    Next
    INDEX
    Explanations

    phrases related to comparisons between different entities

    oai_token-act-pair · gpt-3.5-turbo

    phrases and references related to comparisons and evaluations of different systems or situations

    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
    ©¶æ
    -0.77
    hei
    -0.67
    ole
    -0.66
    ãĤ¢ãĥ«
    -0.66
    ãĤ¤ãĥĪ
    -0.64
    lift
    -0.64
    ademic
    -0.64
    stract
    -0.63
    iple
    -0.62
    wal
    -0.62
    POSITIVE LOGITS
     which
    1.26
     whose
    1.11
     although
    1.06
    which
    1.03
     though
    1.02
     albeit
    1.01
     wherein
    1.00
     where
    0.98
     whereby
    0.96
     namely
    0.96
    Activations Density 0.408%

    No Known Activations