© 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. 15953
    Prev
    Next
    INDEX
    Explanations

    terms related to neural networks or neural activity

    oai_token-act-pair · gpt-3.5-turbo

    references to neural networks and related concepts

    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
    UID
    -0.80
     Rabb
    -0.70
    edit
    -0.68
    Hispanic
    -0.67
    UG
    -0.65
     Christy
    -0.64
     Bundy
    -0.64
    European
    -0.64
     FAT
    -0.63
    _-
    -0.63
    POSITIVE LOGITS
     neural
    1.33
     neur
    1.02
     Neural
    0.93
     tiss
    0.93
     muscles
    0.90
     activation
    0.89
     nets
    0.86
     impulses
    0.86
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.86
     neuron
    0.85
    Activations Density 0.005%

    No Known Activations