© 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. 6-RES-JB
    11. 13850
    Prev
    Next
    INDEX
    Explanations

    instances of the word "after" followed by a noun phrase

    oai_token-act-pair · gpt-3.5-turbo

    repetitive phrases that indicate a sequence or event occurring after a specific incident

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orce
    -0.73
    ________________________________________________________________
    -0.66
     Chosen
    -0.66
    ogenic
    -0.66
    handler
    -0.65
    iction
    -0.64
    plane
    -0.64
    ologist
    -0.63
    favorite
    -0.63
    agram
    -0.62
    POSITIVE LOGITS
    ODUCT
    0.65
     Pew
    0.62
     discussions
    0.60
     backdrop
    0.59
     Bloomberg
    0.59
    PN
    0.59
     Garc
    0.59
    anmar
    0.58
     ..........
    0.58
     developments
    0.57
    Activations Density 0.101%

    No Known Activations