© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 6-RES-JB
    11. 12787
    Prev
    Next
    INDEX
    Explanations

    phrases referring to time intervals such as "last few," "last several," or "last couple."

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating time intervals, particularly those beginning with "over the last"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    osure
    -0.71
    VILLE
    -0.67
    aylor
    -0.65
    uala
    -0.64
     Fail
    -0.64
    minster
    -0.63
     viol
    -0.63
    eele
    -0.61
     Column
    -0.61
    anova
    -0.60
    POSITIVE LOGITS
     decade
    0.97
     generations
    0.94
     millennia
    0.91
     millenn
    0.89
     horizon
    0.89
    ebin
    0.88
     Palestin
    0.86
     decades
    0.83
     centuries
    0.83
     weekend
    0.80
    Activations Density 0.049%

    No Known Activations