© 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. 10-RES-JB
    11. 12058
    Prev
    Next
    INDEX
    Explanations

    phrases related to subscribing to newsletters

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iddles
    -0.61
    FTWARE
    -0.59
    abase
    -0.59
    (-
    -0.56
     hurd
    -0.54
     crosses
    -0.54
     seams
    -0.53
    ================================================================
    -0.53
     ILCS
    -0.52
     torches
    -0.52
    POSITIVE LOGITS
     subscribe
    0.84
     consume
    0.72
     amplify
    0.69
     refresh
    0.67
     receive
    0.67
    raud
    0.66
     keep
    0.66
    register
    0.65
     apply
    0.64
     bookmark
    0.63
    Activations Density 0.033%

    No Known Activations