© 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. 7-RES-JB
    11. 2040
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "the next day" in a sequence of events

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "the next day."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    esse
    -0.90
    overe
    -0.71
    anke
    -0.71
    ocker
    -0.70
    otto
    -0.69
    egal
    -0.67
    emis
    -0.66
    affected
    -0.65
    offs
    -0.65
    gotten
    -0.65
    POSITIVE LOGITS
     Rampage
    0.70
    iatus
    0.69
     onwards
    0.67
    cture
    0.66
    ILA
    0.65
    large
    0.63
    ghan
    0.61
    enium
    0.61
    lins
    0.60
     when
    0.60
    Activations Density 0.079%

    No Known Activations