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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8-RES-JB
    11. 4575
    Prev
    Next
    INDEX
    Explanations

    years and time-related information

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the passage of time and duration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     whiff
    -0.53
    ONSORED
    -0.52
     Yelp
    -0.47
     Scalia
    -0.46
     feces
    -0.45
     mural
    -0.43
     kosher
    -0.42
     Gorsuch
    -0.42
     guiName
    -0.41
    boost
    -0.41
    POSITIVE LOGITS
     withd
    0.55
    Firstly
    0.52
     Firstly
    0.51
    :-
    0.51
    lished
    0.49
     organise
    0.49
    ngth
    0.49
    mble
    0.48
    RAW
    0.47
    sembly
    0.46
    Activations Density 2.250%

    No Known Activations