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. 4-RES-JB
    6. 7628
    Prev
    Next
    INDEX
    Explanations

    mentions of rows, whether they pertain to physical rows or metaphorical instances of the term

    oai_token-act-pair · gpt-3.5-turbo

    references to "row" in various contexts

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

    No Comments

    Negative Logits
    merce
    -0.85
    ãĥ¤
    -0.80
    urated
    -0.78
    omorphic
    -0.74
    urate
    -0.74
    awaru
    -0.68
    ufact
    -0.68
    vironments
    -0.68
    enture
    -0.67
    ascript
    -0.67
    POSITIVE LOGITS
    dy
    1.35
    dies
    1.17
     row
    0.88
    boat
    0.81
    dale
    0.79
    bean
    0.78
    Room
    0.78
     rows
    0.78
    Bre
    0.76
    nd
    0.76
    Activations Density 0.005%

    No Known Activations