© 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. 2-RES-JB
    11. 22005
    Prev
    Next
    INDEX
    Explanations

    instances of people or objects being noticed or seen in various situations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "spotted" indicating observations or sightings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    externalActionCode
    -0.81
    vernment
    -0.79
    nesia
    -0.77
    brance
    -0.76
    mort
    -0.76
    idem
    -0.75
    venge
    -0.74
    atever
    -0.74
    anwhile
    -0.73
    bern
    -0.72
    POSITIVE LOGITS
     spotted
    0.92
    bugs
    0.91
     owl
    0.87
     Owl
    0.78
     Viper
    0.76
    dylib
    0.74
    uca
    0.70
     rods
    0.70
    footed
    0.70
    lights
    0.69
    Activations Density 0.018%

    No Known Activations