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. 9644
    Prev
    Next
    INDEX
    Explanations

    terms related to accommodations or staying in a place

    oai_token-act-pair · gpt-3.5-turbo

    terms related to accommodations and lodging

    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
    aneously
    -0.80
    aneous
    -0.71
    urity
    -0.67
     Blossom
    -0.65
     embryonic
    -0.65
     Sonny
    -0.64
     mined
    -0.64
     McCull
    -0.64
     fingerprint
    -0.62
     disse
    -0.62
    POSITIVE LOGITS
     accommodations
    1.11
     rentals
    1.09
    bnb
    1.03
     accommodation
    1.03
    boat
    0.97
    boats
    0.94
     rental
    0.91
    ommod
    0.88
    ousing
    0.86
     Rent
    0.85
    Activations Density 0.233%

    No Known Activations