© 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. 17042
    Prev
    Next
    INDEX
    Explanations

    references to delicacies and expressions of appreciation

    oai_token-act-pair · gpt-3.5-turbo

    expressions of appreciation and descriptions of delicacies

    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
     Rothschild
    -0.73
     Wall
    -0.72
     Primordial
    -0.70
     Mage
    -0.69
     Fields
    -0.68
     Trip
    -0.66
     Hole
    -0.66
     fingerprints
    -0.65
     Steps
    -0.65
     calculus
    -0.65
    POSITIVE LOGITS
    ately
    1.29
    uously
    1.15
    ably
    1.15
    acies
    1.07
    atures
    1.03
    ality
    1.00
    ators
    0.97
    itives
    0.97
    acy
    0.97
    atively
    0.96
    Activations Density 0.026%

    No Known Activations