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. 1763
    Prev
    Next
    INDEX
    Explanations

    phrases related to high intensity or extreme situations

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of "height" or "level" in various contexts

    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
     Territories
    -0.75
    iott
    -0.75
    tymology
    -0.70
    imei
    -0.69
    prototype
    -0.69
    ictionary
    -0.68
    issors
    -0.65
     coli
    -0.65
     parted
    -0.64
     Scripture
    -0.64
    POSITIVE LOGITS
     unbeliev
    0.87
    Loading
    0.77
     highs
    0.75
     lows
    0.75
     readiness
    0.69
     adrenaline
    0.68
    vez
    0.67
    amina
    0.65
    Demand
    0.65
     realism
    0.64
    Activations Density 0.208%

    No Known Activations