© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 9412
    Prev
    Next
    INDEX
    Explanations

    names or terms related to the name "Johan"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name 'Ohan'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cache
    -0.68
     mod
    -0.65
     sequ
    -0.64
     SCP
    -0.63
     Tacoma
    -0.63
     exhib
    -0.62
     compress
    -0.61
     Cons
    -0.61
     excav
    -0.61
     property
    -0.61
    POSITIVE LOGITS
    ohan
    4.76
    enegger
    1.30
    ahan
    1.27
    ahon
    1.13
    anian
    1.10
    orge
    1.05
    ogan
    1.04
    OTO
    0.94
    ilton
    0.94
    aughs
    0.94
    Activations Density 0.019%

    No Known Activations