© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 0-RES-JB
    11. 4059
    Prev
    Next
    INDEX
    Explanations

    words related to knots and connections

    oai_token-act-pair · gpt-3.5-turbo

    references to knots and connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ario
    -0.90
     Zion
    -0.69
     kidneys
    -0.69
     Mahmoud
    -0.67
    ribution
    -0.66
    aign
    -0.66
    rera
    -0.66
    Dem
    -0.65
    eport
    -0.65
    angel
    -0.64
    POSITIVE LOGITS
     knot
    4.01
     knots
    3.66
     Knot
    2.71
     dots
    1.27
     strands
    1.12
     tangled
    1.03
     strand
    1.02
     beads
    1.02
     entangled
    0.96
     Gap
    0.94
    Activations Density 0.040%

    No Known Activations