© 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. 0-RES-JB
    11. 9433
    Prev
    Next
    INDEX
    Explanations

    words related to transportation or data transfer

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with transitions and transformations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lio
    -0.81
    ASON
    -0.79
    ggle
    -0.76
     stocking
    -0.75
    beer
    -0.72
     gren
    -0.66
     stout
    -0.66
    hitting
    -0.65
    odder
    -0.65
     pall
    -0.65
    POSITIVE LOGITS
     Trans
    3.78
    Trans
    2.48
    trans
    2.22
     trans
    2.16
     TRANS
    1.96
     Transgender
    1.69
    rans
    1.53
     TRAN
    1.49
     transm
    1.44
     Translation
    1.41
    Activations Density 0.010%

    No Known Activations