© 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. 20652
    Prev
    Next
    INDEX
    Explanations

    phrases related to discussing or suggesting further action

    oai_token-act-pair · gpt-3.5-turbo

    special characters or symbols that may indicate emphasis or specific points in the text

    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
     scatter
    -0.66
     Barrier
    -0.66
     habit
    -0.65
     bunk
    -0.64
    OTOS
    -0.64
     shroud
    -0.64
     Samoa
    -0.63
     spiral
    -0.62
     lodging
    -0.62
     guiActiveUnfocused
    -0.62
    POSITIVE LOGITS
    said
    1.02
    say
    0.97
    according
    0.94
    especially
    0.93
    º
    0.91
    £
    0.89
    then
    0.87
    cause
    0.85
    unless
    0.83
    yet
    0.83
    Activations Density 0.119%

    No Known Activations