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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 12819
    Prev
    Next
    INDEX
    Explanations

    verbs related to tracking or hunting down something or someone

    oai_token-act-pair · gpt-3.5-turbo

    the repeated phrase "track down."

    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
    pires
    -0.74
     garn
    -0.69
    iol
    -0.67
    uary
    -0.61
     rack
    -0.61
    mort
    -0.60
    uph
    -0.59
    gae
    -0.58
     propelled
    -0.58
     Antar
    -0.58
    POSITIVE LOGITS
    PsyNetMessage
    0.74
    pell
    0.73
     roots
    0.69
     informants
    0.69
     Jagu
    0.68
    DragonMagazine
    0.68
    ewitness
    0.67
    LOAD
    0.67
    Fax
    0.66
    pter
    0.65
    Activations Density 0.033%

    No Known Activations