© 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. 9335
    Prev
    Next
    INDEX
    Explanations

    terms related to personal qualities and attributes

    oai_token-act-pair · gpt-3.5-turbo

    concepts or phrases indicating growth, distinction, or peculiarities

    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
    _>
    -0.56
    hap
    -0.55
    )=(
    -0.48
    phasis
    -0.48
    ivably
    -0.46
    )"
    -0.45
     NOTICE
    -0.45
    ammy
    -0.44
     ERROR
    -0.43
     Root
    -0.42
    POSITIVE LOGITS
    iaries
    0.51
    onto
    0.50
    dies
    0.49
    packing
    0.48
    tyard
    0.48
    glers
    0.47
    tracks
    0.47
     behav
    0.46
    ²¾
    0.46
    ween
    0.46
    Activations Density 3.150%

    No Known Activations