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. 24079
    Prev
    Next
    INDEX
    Explanations

    instances where someone has been in a specific location

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "I was in" followed by a location or situation

    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
    Availability
    -0.66
     larg
    -0.65
    Includes
    -0.64
     newcomers
    -0.60
    ($
    -0.60
    Jose
    -0.60
     currents
    -0.60
    âĤ¬
    -0.59
    Residents
    -0.59
     strings
    -0.59
    POSITIVE LOGITS
    animate
    0.80
    ordinate
    0.80
    uggle
    0.76
    strument
    0.74
    pport
    0.73
    active
    0.71
     unch
    0.71
    comed
    0.70
    utters
    0.69
    operative
    0.69
    Activations Density 0.222%

    No Known Activations