© 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. 6766
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "Interior"

    oai_token-act-pair · gpt-3.5-turbo

    references to the "Interior" in various contexts

    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
     tet
    -0.68
     β
    -0.66
     sy
    -0.65
     token
    -0.64
     tether
    -0.63
     packets
    -0.63
     lent
    -0.63
     packet
    -0.62
     beta
    -0.62
     sticky
    -0.62
    POSITIVE LOGITS
     Interior
    4.01
     interior
    1.68
     Cabinet
    1.18
     Zin
    1.14
     Agriculture
    1.12
     Environment
    1.09
     EPA
    1.09
     Antiqu
    1.07
     Judiciary
    1.07
     Defense
    1.06
    Activations Density 0.012%

    No Known Activations