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

    Neuronpedia

    APICircuit 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. 9-RES-JB
    6. 3862
    Prev
    Next
    INDEX
    Explanations

    references to the time 45:00 (likely in the context of an event schedule or a specific point in a narrative)

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hers
    -0.67
    nesday
    -0.66
     Chronicle
    -0.64
    elled
    -0.63
     simul
    -0.63
     gifted
    -0.62
    gewater
    -0.62
    ily
    -0.62
    reach
    -0.62
     neighb
    -0.61
    POSITIVE LOGITS
    00
    1.02
    rpm
    0.91
    ACP
    0.89
    678
    0.89
    %-
    0.84
    %
    0.83
     deg
    0.77
    ances
    0.76
    67
    0.76
    50
    0.76
    Activations Density 0.080%

    No Known Activations