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. 7-RES-JB
    6. 20452
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Fe" with varying degrees of emphasis

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific person or character, likely related to someone named Fe

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     GEAR
    -0.71
     Nadu
    -0.69
    worthy
    -0.67
    inating
    -0.66
    DOWN
    -0.66
     ANGEL
    -0.65
    ova
    -0.65
    inates
    -0.63
    inated
    -0.62
     eleph
    -0.62
    POSITIVE LOGITS
    eling
    1.17
    lder
    1.14
    vered
    1.11
    cking
    1.08
    elin
    1.08
    els
    1.07
    ck
    1.06
    ffer
    1.02
    zza
    1.01
    ld
    1.00
    Activations Density 0.032%

    No Known Activations