© 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. 2-RES-JB
    11. 9263
    Prev
    Next
    INDEX
    Explanations

    phrases related to knots or tangles

    oai_token-act-pair · gpt-3.5-turbo

    references to knots, both literal and metaphorical

    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
    nesota
    -0.86
    ONSORED
    -0.84
    anwhile
    -0.74
    ioch
    -0.68
     redistributed
    -0.66
    baugh
    -0.64
    geist
    -0.64
    arthed
    -0.64
     Said
    -0.62
    ourge
    -0.62
    POSITIVE LOGITS
     knot
    1.26
    weed
    1.05
     knots
    0.99
    ties
    0.87
    istani
    0.85
    ty
    0.85
    ishes
    0.81
     strand
    0.80
    locks
    0.79
    hered
    0.77
    Activations Density 0.009%

    No Known Activations