© 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. 7-RES-JB
    11. 12697
    Prev
    Next
    INDEX
    Explanations

    phrases surrounded by quotation marks

    oai_token-act-pair · gpt-3.5-turbo

    quoted phrases or dialogues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ļ½
    -0.79
    stant
    -0.76
    ¿
    -0.75
    ¾
    -0.75
    ãĤ¨ãĥ«
    -0.66
    ¸
    -0.66
    ĻĤ
    -0.65
    ailing
    -0.65
    ctuary
    -0.65
    ãĥ¥
    -0.65
    POSITIVE LOGITS
    /"
    1.17
     moniker
    0.86
     aka
    0.83
     mentality
    0.74
     whereby
    0.70
     designation
    0.70
    aneers
    0.70
     wherein
    0.69
     ("
    0.68
     mantra
    0.68
    Activations Density 0.078%

    No Known Activations