© 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. 2-RES-JB
    11. 5611
    Prev
    Next
    INDEX
    Explanations

    words related to locations and names

    oai_token-act-pair · gpt-3.5-turbo

    instances of the letter "w"

    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
     mosqu
    -0.87
    milo
    -0.84
     distingu
    -0.76
     paraly
    -0.76
     sensitivity
    -0.74
     susceptibility
    -0.74
    İĭ
    -0.74
     tremend
    -0.73
     nomine
    -0.73
     hemor
    -0.73
    POSITIVE LOGITS
    itness
    1.40
    atts
    1.36
    ashington
    1.26
    elcome
    1.25
    restling
    1.16
    edge
    1.12
    ITNESS
    1.09
    izard
    1.09
    reck
    1.08
    ield
    1.06
    Activations Density 0.032%

    No Known Activations