© 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. 7-RES-JB
    11. 1746
    Prev
    Next
    INDEX
    Explanations

    words related to specific names and concepts, particularly those involving repeated letters or unique spellings

    oai_token-act-pair · gpt-3.5-turbo

    words related to various forms of food and utility objects

    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
     piercing
    -0.59
    arching
    -0.51
     Cheong
    -0.50
     Crypto
    -0.50
     holiest
    -0.50
     impuls
    -0.50
     elevation
    -0.49
     Highlands
    -0.49
     mir
    -0.48
    èĢħ
    -0.48
    POSITIVE LOGITS
    vous
    0.78
    ANE
    0.72
    ggle
    0.67
    ortunate
    0.66
    hire
    0.65
    ori
    0.64
    uum
    0.64
    oop
    0.63
    wagen
    0.63
     AAA
    0.63
    Activations Density 0.378%

    No Known Activations