© 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. 2-RES-JB
    6. 18937
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically those related to different fields such as names of places or awards

    oai_token-act-pair · gpt-3.5-turbo

    references to various fields, particularly focusing on the term 'Fields'

    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
     dism
    -0.69
    ILLE
    -0.69
    shapeshifter
    -0.64
    AE
    -0.62
     Fas
    -0.62
    Flight
    -0.61
     Stra
    -0.60
     Trin
    -0.59
    ces
    -0.58
    BILITY
    -0.58
    POSITIVE LOGITS
     fields
    1.02
    hops
    0.99
    fields
    0.98
    matter
    0.92
    chool
    0.89
     irrig
    0.86
    paces
    0.86
    field
    0.83
    mith
    0.83
    heet
    0.81
    Activations Density 0.008%

    No Known Activations