© 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. 9-RES-JB
    11. 23832
    Prev
    Next
    INDEX
    Explanations

    phrases related to time progression

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate sequence or timing of events

    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
    requires
    -0.71
     conspic
    -0.66
    atories
    -0.65
     distinctive
    -0.62
    eer
    -0.62
     preserves
    -0.62
     ®
    -0.61
     embattled
    -0.61
     retains
    -0.60
     endangered
    -0.60
    POSITIVE LOGITS
     awhile
    0.96
     my
    0.85
     puberty
    0.85
     hearing
    0.83
     reading
    0.82
     realizing
    0.81
    ilight
    0.78
     seeing
    0.78
     messing
    0.77
     writing
    0.76
    Activations Density 0.409%

    No Known Activations