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. 6-RES-JB
    6. 3503
    Prev
    Next
    INDEX
    Explanations

    phrases indicating something being in the middle or in-between

    oai_token-act-pair · gpt-3.5-turbo

    the word "between" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iken
    -0.77
    dn
    -0.72
    tu
    -0.71
    ikan
    -0.66
    et
    -0.65
     SPORTS
    -0.64
    DN
    -0.64
    thora
    -0.64
    erve
    -0.64
    atche
    -0.64
    POSITIVE LOGITS
     eras
    0.73
     layers
    0.71
     bouts
    0.71
    heid
    0.68
     worlds
    0.66
     periods
    0.64
     spheres
    0.63
     recess
    0.62
    worldly
    0.62
     stages
    0.61
    Activations Density 0.025%

    No Known Activations