© 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. 588
    Prev
    Next
    INDEX
    Explanations

    preferences between different food items

    oai_token-act-pair · gpt-3.5-turbo

    terms related to preferences, events, and project themes

    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
    atorium
    -0.49
     Thing
    -0.46
     Rifle
    -0.45
    çīĪ
    -0.45
     Horror
    -0.44
     Jol
    -0.43
     Kamp
    -0.43
     VID
    -0.43
    Naz
    -0.43
     Rampage
    -0.42
    POSITIVE LOGITS
    ynthesis
    0.86
    mith
    0.84
    uggest
    0.83
    pring
    0.79
    pread
    0.78
    hip
    0.77
    paces
    0.74
    pace
    0.74
    afety
    0.73
    poon
    0.72
    Activations Density 1.137%

    No Known Activations