© 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. 6-RES-JB
    11. 14400
    Prev
    Next
    INDEX
    Explanations

    proper nouns, possibly names of people or entities

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Billie" and related 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
     sshd
    -0.71
    Wan
    -0.62
     Grayson
    -0.60
     beware
    -0.59
    hiba
    -0.59
    :#
    -0.58
    DEV
    -0.57
     FANTASY
    -0.55
    ORGE
    -0.55
    obook
    -0.54
    POSITIVE LOGITS
    anwhile
    0.62
    rill
    0.60
    swick
    0.60
    urches
    0.59
    EStream
    0.58
    rium
    0.58
    gery
    0.58
    lehem
    0.56
     Genocide
    0.55
    bas
    0.55
    Activations Density 0.359%

    No Known Activations