© 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. 1027
    Prev
    Next
    INDEX
    Explanations

    names or terms with the initials "E" and another character with a number in the activated position

    oai_token-act-pair · gpt-3.5-turbo

    abbreviations or names that start with the letter 'E'

    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
    REL
    -0.72
    xus
    -0.71
    DAQ
    -0.67
    anova
    -0.65
    isky
    -0.63
     XL
    -0.61
    caps
    -0.60
    uties
    -0.59
     kittens
    -0.58
    PF
    -0.58
    POSITIVE LOGITS
    ilon
    0.82
    anasia
    0.79
    vironment
    0.77
    tainment
    0.73
    ascript
    0.71
     Predator
    0.70
    hower
    0.70
    hardt
    0.69
    pecially
    0.68
    Reloaded
    0.68
    Activations Density 0.085%

    No Known Activations