© 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. 2-RES-JB
    11. 17106
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly likely names of entities or places

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "An" followed by various nouns or phrases

    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
    ðŁij
    -0.73
     Bulg
    -0.71
    è¯
    -0.69
    poke
    -0.69
    ï¸ı
    -0.67
    çĶ
    -0.66
    Magikarp
    -0.64
     ;)
    -0.64
     PJ
    -0.63
     Vaugh
    -0.62
    POSITIVE LOGITS
    esthetic
    1.11
    onym
    1.11
    alyses
    1.08
    alogue
    1.08
    omal
    1.07
    alys
    1.06
    omaly
    1.04
    ubis
    0.97
    alyst
    0.93
    notation
    0.92
    Activations Density 0.074%

    No Known Activations