Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 18515
    Prev
    Next
    INDEX
    Explanations

    mentions of the actor "Kua**ff**man" and its variations

    oai_token-act-pair · gpt-3.5-turbo

    the end-of-text token and certain repeated sequences or characters

    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
    xon
    -0.81
    CHO
    -0.65
    ciating
    -0.63
    AAF
    -0.63
    Balt
    -0.62
    MpServer
    -0.61
    ãĥīãĥ©ãĤ´ãĥ³
    -0.60
    SHIP
    -0.60
    senal
    -0.60
     mater
    -0.58
    POSITIVE LOGITS
    erent
    1.14
    mpeg
    1.08
    irms
    1.06
    ords
    1.02
    ees
    1.00
    iculty
    0.95
    shire
    0.94
    erences
    0.94
    erential
    0.91
    rey
    0.90
    Activations Density 0.022%

    No Known Activations