© 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. 2-RES-JB
    11. 19066
    Prev
    Next
    INDEX
    Explanations

    shapes of objects

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of shape

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    incial
    -0.69
    GS
    -0.66
    amily
    -0.65
     Guilty
    -0.65
    iae
    -0.64
    onte
    -0.63
     unpublished
    -0.63
    ILLE
    -0.60
     unanswered
    -0.60
    UTERS
    -0.60
    POSITIVE LOGITS
    shape
    1.20
     shape
    1.16
     Shape
    1.11
     shapes
    1.06
    Shape
    0.88
     shaped
    0.83
     shif
    0.81
     morp
    0.79
    yout
    0.79
    nels
    0.79
    Activations Density 0.018%

    No Known Activations