© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 7-RES-JB
    11. 17280
    Prev
    Next
    INDEX
    Explanations

    references to the Postal Service

    oai_token-act-pair · gpt-3.5-turbo

    references to postal services and mailing systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hov
    -1.05
    aunder
    -1.04
    itsch
    -0.94
    minster
    -0.87
    edin
    -0.86
    eca
    -0.86
    ileaks
    -0.86
    boa
    -0.85
    20439
    -0.84
    ett
    -0.83
    POSITIVE LOGITS
     affairs
    0.77
    fecture
    0.75
     distress
    0.73
     pains
    0.72
    TY
    0.71
     rites
    0.70
     tract
    0.69
     vag
    0.68
     misc
    0.68
     office
    0.68
    Activations Density 0.040%

    No Known Activations