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. 121
    Prev
    Next
    INDEX
    Explanations

    rooms or spaces that are full of something

    oai_token-act-pair · gpt-3.5-turbo

    references to rooms or spaces filled with items or people

    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
     Disciple
    -0.79
    pher
    -0.71
     Pere
    -0.71
    apters
    -0.67
    Downloadha
    -0.66
    ucl
    -0.66
    ovan
    -0.66
    oice
    -0.66
    gemony
    -0.64
     Calder
    -0.64
    POSITIVE LOGITS
    screen
    0.98
    erton
    0.83
    heartedly
    0.81
    ening
    0.79
     blown
    0.79
    grown
    0.77
    width
    0.77
     grown
    0.76
    ness
    0.75
     moon
    0.75
    Activations Density 0.028%

    No Known Activations