© 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. 9-RES-JB
    11. 10411
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions or behaviors

    oai_token-act-pair · gpt-3.5-turbo

    actions and behaviors related to consumption and usage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PHOTOS
    -0.77
    Publisher
    -0.65
     acronym
    -0.65
    HCR
    -0.65
    Merit
    -0.61
    agy
    -0.59
    borgh
    -0.59
    Website
    -0.59
    Represent
    -0.59
    Politics
    -0.58
    POSITIVE LOGITS
     them
    0.99
     these
    0.98
     batches
    0.89
     this
    0.88
     it
    0.85
     lots
    0.81
     TWO
    0.80
     multiple
    0.80
     something
    0.77
     several
    0.76
    Activations Density 0.302%

    No Known Activations