© 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. 7-RES-JB
    11. 2201
    Prev
    Next
    INDEX
    Explanations

    declarative sentences with neutrality

    oai_token-act-pair · gpt-3.5-turbo

    the word "was" in various contexts

    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
    sburg
    -0.92
    uld
    -0.74
    iny
    -0.70
     Spani
    -0.70
    olon
    -0.66
    bury
    -0.65
    inas
    -0.65
    usercontent
    -0.65
    know
    -0.65
     peg
    -0.64
    POSITIVE LOGITS
     widely
    1.03
     designed
    0.99
     intended
    0.98
     aimed
    0.96
     slated
    0.94
     meant
    0.93
     billed
    0.93
     awarded
    0.92
     prompted
    0.92
     housed
    0.92
    Activations Density 0.299%

    No Known Activations