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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 0-RES-JB
    6. 23396
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific name "Fre" with different endings or variations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "Fre" and its variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    illance
    -0.70
     pouch
    -0.69
    ovember
    -0.69
    olson
    -0.67
    invoke
    -0.67
     TOM
    -0.65
     recite
    -0.64
     bowl
    -0.63
    ished
    -0.62
    ishment
    -0.62
    POSITIVE LOGITS
     Fre
    3.82
    Fre
    2.73
    fre
    2.15
     fre
    2.09
     FRE
    1.70
     Freeman
    1.53
     Freak
    1.39
     Frem
    1.34
     Frey
    1.29
     Freem
    1.19
    Activations Density 0.021%

    No Known Activations