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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 0-RES-JB
    11. 17330
    Prev
    Next
    INDEX
    Explanations

    the German word "befehl" or its variations

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the substring "ef"

    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
     mileage
    -0.67
     scam
    -0.66
     Sammy
    -0.66
     Pathfinder
    -0.65
     humming
    -0.62
     Panama
    -0.62
     scams
    -0.61
     Columbia
    -0.61
     swinging
    -0.61
     Chapman
    -0.61
    POSITIVE LOGITS
    ef
    4.36
    efer
    2.03
    efe
    1.82
    EF
    1.54
    eb
    1.51
    ec
    1.45
    ev
    1.29
    ep
    1.27
    eg
    1.26
    ek
    1.26
    Activations Density 0.010%

    No Known Activations