© 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 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. 9-RES-JB
    11. 2250
    Prev
    Next
    INDEX
    Explanations

    phrases indicating something is available for decision-making or consideration

    oai_token-act-pair · gpt-3.5-turbo
    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
    çīĪ
    -0.78
     Ahead
    -0.64
     VIDEOS
    -0.62
     Alone
    -0.62
    mare
    -0.60
    artifacts
    -0.60
    é¾įå
    -0.60
     suffice
    -0.59
     GOODMAN
    -0.59
     Dome
    -0.58
    POSITIVE LOGITS
     grabs
    1.26
     sale
    1.20
     consideration
    1.02
    geries
    1.01
     inspection
    1.01
     scrutiny
    0.96
     renewal
    0.93
     adoption
    0.92
    ked
    0.90
    gery
    0.84
    Activations Density 0.125%

    No Known Activations