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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 3-RES-JB
    6. 19023
    Prev
    Next
    INDEX
    Explanations

    words related to the element "argon."

    oai_token-act-pair · gpt-3.5-turbo

    terms related to arguments in a debate or discussion context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    emetery
    -0.94
    TPS
    -0.76
    idad
    -0.74
    CLASSIFIED
    -0.74
    eor
    -0.74
    arthy
    -0.68
    isSpecialOrderable
    -0.67
    grades
    -0.66
    itizens
    -0.65
    dates
    -0.64
    POSITIVE LOGITS
    uments
    1.39
    ument
    1.21
    uing
    0.97
    acle
    0.86
     Arg
    0.86
    ansas
    0.84
    ued
    0.83
    uably
    0.82
    ues
    0.79
    ij
    0.77
    Activations Density 0.008%

    No Known Activations