© 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. 6525
    Prev
    Next
    INDEX
    Explanations

    phrases indicating considerations or contemplations of actions or decisions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating deliberation or contemplation of actions

    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
    Ware
    -0.74
    Torrent
    -0.72
    Problem
    -0.71
    under
    -0.66
    gen
    -0.65
    CTV
    -0.64
    ritical
    -0.64
    oyal
    -0.63
    runtime
    -0.63
    die
    -0.62
    POSITIVE LOGITS
     alternatives
    0.98
     feasibility
    0.96
     fielding
    0.91
     ways
    0.91
     adopting
    0.91
     whether
    0.90
     merging
    0.89
     deploying
    0.88
     abandoning
    0.87
     hiring
    0.87
    Activations Density 0.229%

    No Known Activations