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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 16257
    Prev
    Next
    INDEX
    Explanations

    phrases related to storytelling or narrative

    oai_token-act-pair · gpt-3.5-turbo

    references to narratives or stories

    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
    erate
    -0.91
    ividual
    -0.77
    bledon
    -0.74
    essors
    -0.72
    apsed
    -0.71
    eele
    -0.70
    uters
    -0.68
    ulty
    -0.67
    ifiers
    -0.67
    atever
    -0.66
    POSITIVE LOGITS
     tales
    1.29
     tale
    1.19
    tale
    1.08
     Tales
    1.02
     Tale
    1.01
    tell
    0.98
     Reincarn
    0.92
    telling
    0.88
    ttes
    0.80
    crow
    0.79
    Activations Density 0.033%

    No Known Activations