© 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. 0-RES-JB
    6. 15708
    Prev
    Next
    INDEX
    Explanations

    references to AAA or AA ratings in the context of finance or exclamation 'Hello there!' after descriptions of violent acts

    oai_token-act-pair · gpt-3.5-turbo

    references to credit ratings and classification systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pompe
    -0.70
     Pars
    -0.69
    gram
    -0.65
    Recipe
    -0.64
    Wilson
    -0.61
     sarc
    -0.60
     Page
    -0.60
     alters
    -0.59
    ricks
    -0.59
    iment
    -0.58
    POSITIVE LOGITS
     AAA
    4.53
    AAA
    2.59
     AA
    2.01
    AAAA
    1.27
    AA
    1.04
     AAC
    1.03
     AHL
    1.01
     DOT
    0.98
     BB
    0.97
     PSP
    0.91
    Activations Density 0.029%

    No Known Activations