© 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 EvalsExportsinterp-engineNEWAPI 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. 5611
    Prev
    Next
    INDEX
    Explanations

    words that start with 's' and are followed by a verb ending in 'ing'

    oai_token-act-pair · gpt-3.5-turbo

    the presence of specific punctuation or symbols

    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
     Wikileaks
    -0.69
    hyde
    -0.69
     unrestricted
    -0.63
     starters
    -0.63
     Pharaoh
    -0.63
     incumbent
    -0.62
     undecided
    -0.62
     Cors
    -0.60
     Sacrament
    -0.59
     RIP
    -0.59
    POSITIVE LOGITS
    outher
    1.22
    ierra
    1.17
    idd
    1.17
    iren
    1.17
    igma
    1.16
    uss
    1.15
    igm
    1.15
    agging
    1.15
    ixties
    1.15
    arah
    1.14
    Activations Density 0.025%

    No Known Activations