© 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. 9343
    Prev
    Next
    INDEX
    Explanations

    instances of the word "crowded"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "crowded" and its variations

    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
    arations
    -0.83
    urai
    -0.77
    hum
    -0.76
    shock
    -0.75
    aration
    -0.74
    istry
    -0.73
     derive
    -0.71
    ministic
    -0.69
    ibur
    -0.68
    clair
    -0.66
    POSITIVE LOGITS
     pores
    0.81
     queues
    0.80
     spaces
    0.78
     vacancies
    0.78
     arenas
    0.74
     crowded
    0.73
     intersections
    0.72
     streets
    0.72
     halls
    0.71
    pread
    0.71
    Activations Density 0.040%

    No Known Activations