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. 4-RES-JB
    6. 19205
    Prev
    Next
    INDEX
    Explanations

    words related to exploring deeply or investigating thoroughly

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to exploration or deep engagement with topics

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

    No Comments

    Negative Logits
    runners
    -0.72
    evidence
    -0.71
    Islamic
    -0.70
    1920
    -0.68
    urers
    -0.67
    orate
    -0.66
    Gary
    -0.65
    say
    -0.64
    istically
    -0.61
    Pakistan
    -0.59
    POSITIVE LOGITS
     dive
    1.12
     Dive
    0.99
     diving
    0.93
     dives
    0.91
     hitter
    0.85
     delve
    0.81
     earthqu
    0.80
    xit
    0.78
    EStream
    0.76
    hower
    0.76
    Activations Density 0.015%

    No Known Activations