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. 7-RES-JB
    6. 5497
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "beef" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "beef" and its variations

    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
    pmwiki
    -0.83
    âĸ¬
    -0.80
    ISTER
    -0.67
    âĸ¬âĸ¬
    -0.64
     Archangel
    -0.63
     Scotia
    -0.62
     PV
    -0.62
     Spac
    -0.62
    antics
    -0.61
     MSI
    -0.61
    POSITIVE LOGITS
    cake
    1.20
     jer
    1.03
    ington
    1.01
    skin
    0.96
    ste
    0.91
    SourceFile
    0.88
    unct
    0.84
    alos
    0.83
    quarters
    0.83
    bone
    0.82
    Activations Density 0.018%

    No Known Activations