Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 7968
    Prev
    Next
    INDEX
    Explanations

    mentions of traveling or being on the road

    oai_token-act-pair · gpt-3.5-turbo

    references to travel or movement, particularly involving the concept of "the road."

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

    No Comments

    Negative Logits
    ividual
    -0.76
    enance
    -0.71
    ority
    -0.70
    illian
    -0.68
    ancial
    -0.67
    ento
    -0.67
    rencies
    -0.67
     Mons
    -0.66
    cius
    -0.66
    ulu
    -0.65
    POSITIVE LOGITS
    trip
    1.07
    block
    0.96
    ways
    0.92
    blocks
    0.91
    cycle
    0.89
    lane
    0.87
    road
    0.83
    fare
    0.82
     road
    0.81
    runner
    0.79
    Activations Density 0.016%

    No Known Activations