© 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. 8-RES-JB
    11. 23468
    Prev
    Next
    INDEX
    Explanations

    phrases related to filling gaps or voids

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to filling gaps or positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    conduct
    -0.73
    edu
    -0.70
     Married
    -0.69
    otiation
    -0.69
    rules
    -0.67
    peer
    -0.67
    rust
    -0.66
    hess
    -0.66
    lik
    -0.65
    mut
    -0.65
    POSITIVE LOGITS
     coffers
    1.36
     gaps
    1.22
     void
    1.07
     gap
    1.06
     holes
    0.99
     pores
    0.97
     niche
    0.97
     vacancies
    0.97
     vacancy
    0.95
     emptiness
    0.94
    Activations Density 0.139%

    No Known Activations