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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 2102
    Prev
    Next
    INDEX
    Explanations

    references to the Congressional Budget Office (CBO)

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the Congressional Budget Office (CBO) and its estimates or analyses

    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
     Sussex
    -0.75
    ances
    -0.70
     Belg
    -0.68
     Thames
    -0.67
    Else
    -0.67
     Fasc
    -0.67
    "]=>
    -0.66
    stro
    -0.65
     WhatsApp
    -0.64
    opathy
    -0.61
    POSITIVE LOGITS
     CBO
    1.07
    enhagen
    0.95
    TION
    0.85
    bage
    0.79
    µ
    0.77
     resil
    0.77
    enei
    0.76
    vernment
    0.74
     pegged
    0.72
    TS
    0.72
    Activations Density 0.009%

    No Known Activations