© 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. 4-RES-JB
    11. 20373
    Prev
    Next
    INDEX
    Explanations

    phrases related to rules, regulations, or conditions

    oai_token-act-pair · gpt-3.5-turbo

    references to legal or formal regulations

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

    No Comments

    Negative Logits
    Magikarp
    -0.76
     palms
    -0.63
    MAT
    -0.63
     Derby
    -0.62
     nerve
    -0.62
     Devils
    -0.60
    âĺħâĺħ
    -0.60
     Eclipse
    -0.59
     Garfield
    -0.58
     Prescott
    -0.57
    POSITIVE LOGITS
    ally
    1.26
    ality
    1.13
    alities
    1.01
    arian
    0.93
    arians
    0.93
    ions
    0.90
    folios
    0.86
    aments
    0.83
    atively
    0.82
    ional
    0.82
    Activations Density 0.010%

    No Known Activations