© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 9-RES-JB
    11. 19691
    Prev
    Next
    INDEX
    Explanations

    terms with special characters

    oai_token-act-pair · gpt-3.5-turbo

    special characters or unusual symbols within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ipop
    -0.76
    oresc
    -0.74
     Beir
    -0.73
    othal
    -0.72
     Kush
    -0.65
    iary
    -0.65
    ortium
    -0.64
    inx
    -0.64
    acus
    -0.64
    iferation
    -0.63
    POSITIVE LOGITS
     ��������
    0.87
    ternity
    0.84
     ����
    0.84
    taboola
    0.78
    me
    0.77
    mons
    0.76
    âĤ¬
    0.75
    ¢
    0.74
    tis
    0.74
    ãĤ§
    0.73
    Activations Density 0.024%

    No Known Activations