© 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. 10-RES-JB
    11. 5100
    Prev
    Next
    INDEX
    Explanations

    the word "after" followed by some context which is not clearly specific

    oai_token-act-pair · gpt-3.5-turbo

    the phrase 'shortly after' in various contexts indicating a temporal sequence of events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ahime
    -0.89
    ãĤ¦ãĤ¹
    -0.84
    ascript
    -0.80
    ãĥĥ
    -0.79
    ãĤ¡
    -0.74
    venants
    -0.72
    iliated
    -0.72
    anges
    -0.71
    uph
    -0.71
    anium
    -0.71
    POSITIVE LOGITS
     midnight
    1.29
     noon
    1.10
     arriving
    1.08
     Thanksgiving
    1.06
     sunset
    1.01
     sunrise
    1.01
     Christmas
    0.98
     announcing
    0.92
     leaving
    0.91
    noon
    0.91
    Activations Density 0.078%

    No Known Activations