© 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. 1-RES-JB
    6. 18693
    Prev
    Next
    INDEX
    Explanations

    words related to predictions or warnings

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "fore."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    REDACTED
    -0.71
     Paste
    -0.69
    OPLE
    -0.67
    USE
    -0.66
     Ou
    -0.65
    å°Ĩ
    -0.63
     Stain
    -0.61
    BuyableInstoreAndOnline
    -0.61
     Shed
    -0.61
    RED
    -0.61
    POSITIVE LOGITS
     fore
    1.21
    shore
    1.05
    shadow
    1.04
    warn
    1.02
    runner
    0.94
    father
    0.92
    sight
    0.92
    told
    0.92
    fore
    0.89
     Fore
    0.88
    Activations Density 0.004%

    No Known Activations