© 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. 2-RES-JB
    11. 21140
    Prev
    Next
    INDEX
    Explanations

    sequences of actions or events

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "sequence" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sburgh
    -0.87
    lying
    -0.87
    ryn
    -0.84
    enthal
    -0.74
    dom
    -0.70
    aghd
    -0.70
    young
    -0.70
    initions
    -0.68
    rogens
    -0.68
    undai
    -0.68
    POSITIVE LOGITS
     sequence
    1.22
     Sequence
    1.21
     sequences
    1.09
    ĸļ
    0.97
     repeats
    0.80
     sequencing
    0.78
    RIPT
    0.72
     Transcript
    0.71
    uality
    0.71
     queues
    0.71
    Activations Density 0.009%

    No Known Activations