© 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 EvalsExportsinterp-engineNEWAPI 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. 4157
    Prev
    Next
    INDEX
    Explanations

    sentences in a mix of different fonts and symbols where consecutive words start with the same letter

    oai_token-act-pair · gpt-3.5-turbo

    unusual or non-standard characters and symbols

    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
    atche
    -0.82
    aday
    -0.75
     Constantine
    -0.74
     Frie
    -0.70
     Forth
    -0.69
     Patterson
    -0.67
     PSU
    -0.65
    acles
    -0.63
    anwhile
    -0.62
    avering
    -0.61
    POSITIVE LOGITS
    Ĥ¬
    1.42
    Ĭ
    1.40
    §
    1.36
    ħĭ
    1.29
    ²
    1.23
    ¹
    1.22
    º
    1.22
    ĸ
    1.21
    ĭ
    1.21
    ļ
    1.20
    Activations Density 0.012%

    No Known Activations