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. 3-RES-JB
    6. 2079
    Prev
    Next
    INDEX
    Explanations

    references to the state of Texas

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Texas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    theless
    -0.97
    ãĥĭ
    -0.80
    ogle
    -0.78
    fman
    -0.76
    */(
    -0.75
    oser
    -0.71
    uchin
    -0.70
    onymous
    -0.70
    bable
    -0.68
    umbai
    -0.67
    POSITIVE LOGITS
     Instruments
    1.14
     Texans
    0.92
     Longh
    0.91
     Rangers
    0.87
     Tribune
    0.82
     Tech
    0.82
    Texas
    0.80
     Texas
    0.79
    iens
    0.76
     Railroad
    0.76
    Activations Density 0.016%

    No Known Activations