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

    Neuronpedia

    APICircuit 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. 2-RES-JB
    6. 24466
    Prev
    Next
    INDEX
    Explanations

    scientific terms related to atmospheric CO2 levels

    oai_token-act-pair · gpt-3.5-turbo

    references to carbon dioxide (CO2) concentrations

    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
    lihood
    -0.90
    ions
    -0.77
     Brach
    -0.76
    saf
    -0.76
    nik
    -0.72
    =\"
    -0.68
    nikov
    -0.67
    soever
    -0.67
    cgi
    -0.66
    DragonMagazine
    -0.65
    POSITIVE LOGITS
    CO
    1.01
     CO
    0.98
    VO
    0.90
    OPER
    0.89
    CHR
    0.83
    INC
    0.79
    KE
    0.78
    OP
    0.77
    VER
    0.77
    FF
    0.77
    Activations Density 0.006%

    No Known Activations