© 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. 3-RES-JB
    11. 21004
    Prev
    Next
    INDEX
    Explanations

    specific names and terms

    oai_token-act-pair · gpt-3.5-turbo

    names and terms related to specific people, places, and objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    swick
    -1.07
    rition
    -0.90
    ences
    -0.85
    lines
    -0.83
    @#&
    -0.79
    ptroller
    -0.79
    alions
    -0.77
    stuff
    -0.76
    NEY
    -0.75
    entials
    -0.74
    POSITIVE LOGITS
     Fey
    1.12
     Maya
    0.91
    ushima
    0.87
    isan
    0.79
    ouf
    0.72
    ura
    0.72
     Khal
    0.67
    ointed
    0.67
    olin
    0.67
     Mia
    0.67
    Activations Density 0.017%

    No Known Activations