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. 9-RES-JB
    6. 22
    Prev
    Next
    INDEX
    Explanations

    phrases related to research and evaluation, such as discussing causes, processes, measurements, and assessments

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with causes, organizations, and ecological or community-related topics

    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
    ernels
    -0.88
    aughs
    -0.85
    ooks
    -0.82
    bats
    -0.81
    pees
    -0.80
    ummies
    -0.79
    shirts
    -0.79
    atives
    -0.79
    nces
    -0.77
     iPads
    -0.77
    POSITIVE LOGITS
    's
    0.81
    ogram
    0.80
     whose
    0.76
    worker
    0.76
     undergoing
    0.70
     scientist
    0.69
    abase
    0.69
    atical
    0.67
     applicant
    0.67
    uble
    0.67
    Activations Density 0.387%

    No Known Activations