© 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. 4-RES-JB
    11. 10384
    Prev
    Next
    INDEX
    Explanations

    the word "tent" followed by a number indicating a level of importance or quality

    oai_token-act-pair · gpt-3.5-turbo

    references to tents and related camping concepts

    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
    EVA
    -0.68
    ÃĽ
    -0.65
    Words
    -0.63
    obbies
    -0.62
     symmetry
    -0.62
    bye
    -0.61
     Cuomo
    -0.59
    dimensional
    -0.58
     fats
    -0.57
     neurolog
    -0.56
    POSITIVE LOGITS
    atively
    1.35
    acle
    1.29
    pole
    1.18
    acles
    1.05
     tent
    0.98
     pole
    0.89
    acular
    0.89
     encamp
    0.89
     flap
    0.86
     tents
    0.85
    Activations Density 0.012%

    No Known Activations