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. 8-RES-JB
    6. 16224
    Prev
    Next
    INDEX
    Explanations

    prayers or legal references from documents

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to reports or evaluations of programs or documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Flavoring
    -0.81
    ukong
    -0.77
    enery
    -0.69
    peria
    -0.69
    joice
    -0.67
    kees
    -0.65
    BILITIES
    -0.64
     cultures
    -0.64
    obbies
    -0.63
    izons
    -0.63
    POSITIVE LOGITS
     dated
    1.07
     titled
    1.03
     headlined
    0.98
     authored
    0.98
     published
    0.92
    dated
    0.91
    itled
    0.90
     aimed
    0.89
     reprinted
    0.89
     summar
    0.89
    Activations Density 0.758%

    No Known Activations