© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 12619
    Prev
    Next
    INDEX
    Explanations

    dates written in the format "mid-YYYY" and physical locations

    oai_token-act-pair · gpt-3.5-turbo

    references to time periods, specifically those formatted as "mid-year"

    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
     AVG
    -0.77
     Cosponsors
    -0.73
    ħĭ
    -0.69
     DRAG
    -0.67
     QR
    -0.65
    ã쮿
    -0.64
     Neville
    -0.63
     SOS
    -0.62
    éĹĺ
    -0.61
     Compass
    -0.61
    POSITIVE LOGITS
    round
    1.08
    sent
    1.03
    level
    1.03
    trial
    1.01
    sized
    1.00
    season
    0.97
    term
    0.97
    century
    0.97
    distance
    0.97
    earth
    0.96
    Activations Density 0.031%

    No Known Activations