© 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. 2253
    Prev
    Next
    INDEX
    Explanations

    phrases related to difficulty or impossibility

    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
    Happy
    -0.80
    isode
    -0.79
    oward
    -0.75
    liber
    -0.75
     Merry
    -0.71
    Insp
    -0.70
     Celebr
    -0.70
    Nice
    -0.67
    Prom
    -0.66
    femin
    -0.65
    POSITIVE LOGITS
     cumbers
    1.16
     cumbersome
    1.08
     require
    1.05
     uncertainties
    1.05
     requires
    1.04
     complexities
    1.01
     unpredictable
    1.00
     unpredict
    1.00
     unavoid
    0.99
     complicate
    0.98
    Activations Density 0.913%

    No Known Activations