© 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. 23745
    Prev
    Next
    INDEX
    Explanations

    terms related to growth or enhancement

    oai_token-act-pair · gpt-3.5-turbo

    terms related to growth or enhancement

    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
    mates
    -0.75
    atom
    -0.69
     Bowman
    -0.68
    stones
    -0.68
    ician
    -0.68
    mia
    -0.66
    gets
    -0.66
    aries
    -0.66
    icians
    -0.65
    ellow
    -0.65
    POSITIVE LOGITS
     exponentially
    0.99
     awareness
    0.90
     likelihood
    0.85
     amounts
    0.82
     subsequ
    0.80
    xual
    0.80
     visibility
    0.80
     effic
    0.79
     sidx
    0.78
     arousal
    0.78
    Activations Density 0.047%

    No Known Activations