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. 1-RES-JB
    6. 3995
    Prev
    Next
    INDEX
    Explanations

    the word "silver" with a strong activation value

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "silver."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    =-=-=-=-
    -0.84
    rina
    -0.79
    unct
    -0.79
    lov
    -0.78
    LER
    -0.76
    SPONSORED
    -0.76
    etically
    -0.76
    çīĪ
    -0.73
     Gutenberg
    -0.73
    cause
    -0.71
    POSITIVE LOGITS
     silver
    1.17
     iod
    1.08
    silver
    0.97
     medal
    0.94
     bronze
    0.88
     coin
    0.85
     bull
    0.85
     calf
    0.83
     coins
    0.83
     gold
    0.82
    Activations Density 0.005%

    No Known Activations