© 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
    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. 15595
    Prev
    Next
    INDEX
    Explanations

    sentences starting with a number followed by a period or a colon

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "1" used as a reference point or a marker in various contexts

    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
    thinkable
    -0.74
    awaru
    -0.71
     fences
    -0.69
    bent
    -0.67
     Lumpur
    -0.67
    orative
    -0.66
    apon
    -0.65
     roofs
    -0.64
     modelling
    -0.64
     hygiene
    -0.64
    POSITIVE LOGITS
    Password
    1.32
    125
    1.16
    120
    1.08
    st
    1.07
     Corinthians
    1.06
    128
    1.00
    000000
    0.98
    ½
    0.89
    123
    0.88
    0000000
    0.82
    Activations Density 0.068%

    No Known Activations