© 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. 14741
    Prev
    Next
    INDEX
    Explanations

    references to specific years or time periods

    oai_token-act-pair · gpt-3.5-turbo

    phrases associated with shared experiences or collective knowledge

    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
    ...)
    -0.61
    âĢ¦)
    -0.60
    !)
    -0.59
    -)
    -0.57
    )"
    -0.54
    âĢ¦]
    -0.53
     })
    -0.52
    Loading
    -0.51
    \-
    -0.51
     physic
    -0.50
    POSITIVE LOGITS
    etheless
    1.04
    iannopoulos
    0.73
     âĵĺ
    0.60
     Pruitt
    0.59
    abbit
    0.56
    AFP
    0.56
     Trotsky
    0.55
     largeDownload
    0.55
    collect
    0.54
     Mulcair
    0.54
    Activations Density 2.640%

    No Known Activations