© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 10657
    Prev
    Next
    INDEX
    Explanations

    terms related to the concentration of atmospheric CO2

    oai_token-act-pair · gpt-3.5-turbo

    references to carbon dioxide concentrations

    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
    lihood
    -1.04
    DragonMagazine
    -0.87
     Brach
    -0.83
    doms
    -0.75
    ions
    -0.71
    nik
    -0.70
     Pry
    -0.69
    soever
    -0.68
    uyomi
    -0.68
     Kut
    -0.67
    POSITIVE LOGITS
    CO
    0.91
     CO
    0.84
    CHR
    0.84
    VO
    0.82
    VERT
    0.81
    OPER
    0.78
    OL
    0.78
     Colo
    0.77
    INC
    0.76
    JO
    0.75
    Activations Density 0.005%

    No Known Activations