© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 3-RES-JB
    11. 23207
    Prev
    Next
    INDEX
    Explanations

    names of programming elements marked with 'object'

    oai_token-act-pair · gpt-3.5-turbo

    references to objects in programming contexts

    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
     millenn
    -1.02
    mph
    -0.86
    hiba
    -0.78
    DAY
    -0.77
    icago
    -0.76
    cling
    -0.74
    HAEL
    -0.74
    aturdays
    -0.74
    ornia
    -0.73
    creen
    -0.73
    POSITIVE LOGITS
     Object
    0.93
     objects
    0.91
    object
    0.88
    objects
    0.85
     object
    0.84
     obj
    0.83
     Objects
    0.82
     Obj
    0.78
     Token
    0.77
    ifier
    0.77
    Activations Density 0.009%

    No Known Activations