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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 12-RES-JB
    11. 3488
    Prev
    Next
    INDEX
    Explanations

    comparative adjectives

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    phrases indicating actions and behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    "},"
    -0.61
    etus
    -0.60
     Secondly
    -0.59
    clusive
    -0.57
    Secondly
    -0.57
    iesta
    -0.56
     Newsp
    -0.54
    clusion
    -0.53
    dp
    -0.53
    tro
    -0.52
    POSITIVE LOGITS
     like
    2.02
    like
    1.75
     LIKE
    1.63
     Like
    1.50
    Like
    1.48
     akin
    1.23
     alike
    1.15
     unlike
    1.12
     similar
    1.09
     analogous
    1.08
    Activations Density 0.291%

    No Known Activations