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. 2-RES-JB
    6. 9066
    Prev
    Next
    INDEX
    Explanations

    names or terms related to the concept of "Research" or "Resolution."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "Res" or related references in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Icelandic
    -0.71
    aneers
    -0.68
    matically
    -0.66
     CMS
    -0.66
    swick
    -0.66
    tie
    -0.64
     Sark
    -0.63
    DragonMagazine
    -0.63
    glers
    -0.63
    rious
    -0.62
    POSITIVE LOGITS
    olutions
    1.18
    istant
    1.16
    olve
    1.16
    idency
    1.12
    istance
    1.07
    idence
    1.06
    olves
    1.05
    olution
    1.04
    erves
    1.04
    olved
    1.04
    Activations Density 0.010%

    No Known Activations