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. 9-RES-JB
    6. 6761
    Prev
    Next
    INDEX
    Explanations

    financial and numerical terms within specific contexts

    oai_token-act-pair · gpt-3.5-turbo

    statistical data related to the frequency of specific demographic events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lihood
    -0.74
    ãĤ´ãĥ³
    -0.64
    xff
    -0.60
    ational
    -0.59
    ãĤ¨ãĥ«
    -0.59
    gling
    -0.58
    Exit
    -0.57
    apego
    -0.57
    bill
    -0.56
    pex
    -0.56
    POSITIVE LOGITS
     Duration
    0.74
     thereafter
    0.69
    ules
    0.68
     Seller
    0.67
    ulu
    0.62
     Ends
    0.62
     Tone
    0.61
     Participants
    0.60
    avy
    0.59
     Includes
    0.58
    Activations Density 0.030%

    No Known Activations