© 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. 3-RES-JB
    6. 9581
    Prev
    Next
    INDEX
    Explanations

    words related to actions or characteristics of people or things

    oai_token-act-pair · gpt-3.5-turbo

    key action verbs that indicate interactions and relationships

    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
     Palestin
    -0.74
    FTWARE
    -0.73
     reluct
    -0.70
     behavi
    -0.68
     encount
    -0.67
     tyr
    -0.66
     streng
    -0.66
    olesc
    -0.65
     afore
    -0.63
     Registration
    -0.62
    POSITIVE LOGITS
    ingly
    0.98
    ings
    0.88
    eth
    0.71
     themselves
    0.69
    ously
    0.68
    ably
    0.68
     Maher
    0.65
    fully
    0.65
    ilies
    0.64
    glers
    0.64
    Activations Density 0.678%

    No Known Activations