© 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. 8-RES-JB
    11. 10253
    Prev
    Next
    INDEX
    Explanations

    phrases related to emphasis on a particular point

    oai_token-act-pair · gpt-3.5-turbo

    references to time or temporal connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ecided
    -0.66
    artifacts
    -0.64
    renheit
    -0.63
    tons
    -0.63
    itary
    -0.62
    eal
    -0.61
    lift
    -0.60
    Reviewer
    -0.59
    packages
    -0.58
    ansas
    -0.57
    POSITIVE LOGITS
     outset
    1.18
     moment
    1.08
     behest
    1.02
     conclusion
    0.99
     end
    0.97
     forefront
    0.88
     same
    0.85
     glance
    0.81
     beginning
    0.81
     bottom
    0.81
    Activations Density 0.074%

    No Known Activations