© 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. 17613
    Prev
    Next
    INDEX
    Explanations

    references to different fruits (both specific and general)

    oai_token-act-pair · gpt-3.5-turbo

    references to fruits

    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
    ndum
    -0.71
    division
    -0.70
    etimes
    -0.66
     principals
    -0.64
    ahime
    -0.63
    gettable
    -0.63
    tz
    -0.62
    izons
    -0.62
    leaders
    -0.61
    oulder
    -0.60
    POSITIVE LOGITS
     fruits
    1.09
    urance
    0.96
    ãĥ¼ãĥĨãĤ£
    0.94
    æĦ
    0.89
    ãĥ¼ãĤ¯
    0.84
    issance
    0.80
    urer
    0.77
    urers
    0.76
    romeda
    0.75
     reap
    0.75
    Activations Density 0.014%

    No Known Activations