© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 18274
    Prev
    Next
    INDEX
    Explanations

    words related to explorations and expeditions

    oai_token-act-pair · gpt-3.5-turbo

    references to expeditions and exploration activities

    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
    colo
    -0.91
    corn
    -0.89
    practice
    -0.79
    pace
    -0.74
    gone
    -0.72
    akia
    -0.69
    dos
    -0.67
    Federal
    -0.67
    comes
    -0.66
    rael
    -0.66
    POSITIVE LOGITS
     expedition
    1.32
     Expedition
    1.20
     Everest
    0.98
    ngth
    0.91
    naire
    0.85
     exped
    0.83
     explorer
    0.82
    arily
    0.81
     eleph
    0.81
    naires
    0.80
    Activations Density 0.009%

    No Known Activations