© 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. 2-RES-JB
    6. 9120
    Prev
    Next
    INDEX
    Explanations

    words related to physical locations or settings

    oai_token-act-pair · gpt-3.5-turbo

    references to "mills" or related terminology in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Malays
    -0.77
    oÄŁ
    -0.76
    TAG
    -0.70
    lia
    -0.68
     affili
    -0.67
     Bulgar
    -0.66
    bal
    -0.65
     prime
    -0.64
    Barn
    -0.63
    members
    -0.63
    POSITIVE LOGITS
    iard
    1.02
    inger
    0.97
    sburg
    0.96
    hops
    0.86
    chool
    0.85
    espie
    0.84
    uminati
    0.83
    ills
    0.82
    ibrary
    0.82
    avascript
    0.80
    Activations Density 0.005%

    No Known Activations