© 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. 4-RES-JB
    11. 7269
    Prev
    Next
    INDEX
    Explanations

    phrases or contexts related to a specific event or concept named "Day."

    oai_token-act-pair · gpt-3.5-turbo

    references to specific days or events

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

    No Comments

    Negative Logits
     crate
    -0.80
    emort
    -0.76
    essee
    -0.75
    acters
    -0.74
    ancial
    -0.74
    umbn
    -0.73
    ACTED
    -0.73
     glim
    -0.73
     gren
    -0.71
    ngth
    -0.70
    POSITIVE LOGITS
    dream
    1.35
    break
    0.89
    flower
    0.83
     Day
    0.81
     Parade
    0.80
    care
    0.79
    tri
    0.77
     Massacre
    0.76
    lights
    0.76
    long
    0.75
    Activations Density 0.031%

    No Known Activations