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. 8-RES-JB
    6. 23382
    Prev
    Next
    INDEX
    Explanations

    mentions of the drug "n-aloxone" in medical contexts

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "ox" or references related to the opioid naloxone

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     truce
    -0.71
     Shades
    -0.67
     rece
    -0.66
     disemb
    -0.66
    ¢
    -0.63
    aiden
    -0.62
     conflic
    -0.62
     resemblance
    -0.61
     maj
    -0.60
     fries
    -0.60
    POSITIVE LOGITS
    imity
    1.15
    eus
    0.99
    idation
    0.98
    peria
    0.98
    iao
    0.94
    es
    0.90
    nard
    0.90
    xi
    0.89
     Machina
    0.89
    ozo
    0.88
    Activations Density 0.029%

    No Known Activations