Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 1265
    Prev
    Next
    INDEX
    Explanations

    words related to market research and analysis

    oai_token-act-pair · gpt-3.5-turbo

    references to market conditions or trends

    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
    ignt
    -0.79
     Mountains
    -0.75
    ersen
    -0.72
    tein
    -0.71
     Fas
    -0.69
     Chapel
    -0.68
    isner
    -0.67
    racuse
    -0.67
     Lak
    -0.63
    owicz
    -0.63
    POSITIVE LOGITS
    places
    1.38
    eers
    1.14
    hare
    1.05
    eer
    0.87
     markets
    0.84
    eering
    0.82
    daq
    0.81
     marketplace
    0.77
    place
    0.74
     guiActiveUnfocused
    0.72
    Activations Density 0.026%

    No Known Activations