© 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. 12797
    Prev
    Next
    INDEX
    Explanations

    actions or events described in the present or future tense

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to events and their circumstances

    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
    quartered
    -0.82
    uits
    -0.59
     Sun
    -0.57
     Fortune
    -0.56
     sax
    -0.55
    peria
    -0.54
    yne
    -0.54
    Introduced
    -0.53
     arrivals
    -0.53
     Flavoring
    -0.53
    POSITIVE LOGITS
     sooner
    0.83
     beforehand
    0.67
     somehow
    0.64
     someday
    0.64
     itself
    0.63
     tomorrow
    0.62
     somew
    0.61
     replay
    0.60
     ASAP
    0.60
     BEFORE
    0.59
    Activations Density 1.057%

    No Known Activations