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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 21961
    Prev
    Next
    INDEX
    Explanations

    references to outdoor activities, especially hiking and backpacking

    oai_token-act-pair · gpt-3.5-turbo

    terms related to outdoor activities and hiking

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rase
    -0.79
    ysis
    -0.71
     iod
    -0.71
     lobe
    -0.71
    rate
    -0.70
     Frieza
    -0.69
    metics
    -0.66
    rences
    -0.64
    relation
    -0.64
    eon
    -0.64
    POSITIVE LOGITS
     hiking
    1.09
     camping
    0.94
     Carib
    0.92
    erness
    0.89
     Wilderness
    0.89
     hikers
    0.88
     expedition
    0.85
     biking
    0.84
    leigh
    0.83
     Trails
    0.81
    Activations Density 0.055%

    No Known Activations