© 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. 11-RES-JB
    11. 6162
    Prev
    Next
    INDEX
    Explanations

    days of the week or time-related terms

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to daily activities and routines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    essee
    -0.77
     Franch
    -0.73
     ILCS
    -0.69
    ationally
    -0.69
    ACTED
    -0.67
     Reincarnated
    -0.65
    ystem
    -0.65
     constitu
    -0.65
     Sins
    -0.65
     Mellon
    -0.63
    POSITIVE LOGITS
    dream
    1.68
    care
    1.44
    lights
    1.13
    job
    1.12
    jobs
    1.11
    break
    1.10
    trip
    1.08
    tri
    1.04
    long
    1.02
    light
    0.98
    Activations Density 0.061%

    No Known Activations