© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 14124
    Prev
    Next
    INDEX
    Explanations

    phrases related to escalation or intensifying actions

    oai_token-act-pair · gpt-3.5-turbo

    ellipses or pauses in text that indicate interruption or continuation of thought

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
     attest
    -0.68
     merit
    -0.66
    osaurus
    -0.64
     replacement
    -0.64
     felon
    -0.62
     disav
    -0.62
     preference
    -0.61
    rette
    -0.60
    eers
    -0.60
    ouver
    -0.60
    POSITIVE LOGITS
    BUT
    0.98
    why
    0.96
    oops
    0.86
    eh
    0.85
    ind
    0.84
    until
    0.84
    right
    0.82
    interesting
    0.82
     âĢİ
    0.81
    yet
    0.80
    Activations Density 0.040%

    No Known Activations