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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 8-RES-JB
    6. 5835
    Prev
    Next
    INDEX
    Explanations

    phrases related to utilizing or accessing resources or opportunities

    oai_token-act-pair · gpt-3.5-turbo

    the concept of utilizing or accessing resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     discipl
    -0.65
     suppose
    -0.62
    ب
    -0.62
    itary
    -0.61
    cember
    -0.61
     prohibiting
    -0.59
    adder
    -0.59
     Boxing
    -0.58
    ateur
    -0.58
    husband
    -0.58
    POSITIVE LOGITS
    uries
    1.17
    ioned
    0.84
    prise
    0.75
    ibly
    0.75
    roots
    0.74
     electrodes
    0.73
     energies
    0.71
     taps
    0.70
     Byrne
    0.68
    aptic
    0.67
    Activations Density 0.041%

    No Known Activations