© 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. 1-RES-JB
    11. 14137
    Prev
    Next
    INDEX
    Explanations

    the word "Hendricks"

    oai_token-act-pair · gpt-3.5-turbo

    the names of individual players and their mentions in a sports context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     corrid
    -0.75
    LET
    -0.67
    socket
    -0.66
    menu
    -0.65
    Dead
    -0.65
    Availability
    -0.65
    acan
    -0.64
    Cub
    -0.64
     paralyzed
    -0.63
    bowl
    -0.63
    POSITIVE LOGITS
    ueller
    0.92
    vous
    0.91
    eor
    0.88
    annis
    0.88
    edia
    0.82
    vironment
    0.82
    ndra
    0.82
    rup
    0.81
    erest
    0.80
    ppelin
    0.77
    Activations Density 0.036%

    No Known Activations