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. 9736
    Prev
    Next
    INDEX
    Explanations

    numeric values with specific patterns, possibly related to measurements or calculations

    oai_token-act-pair · gpt-3.5-turbo

    numerical values and measurements

    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
    rollers
    -0.73
     Tycoon
    -0.64
    ennes
    -0.63
     preservation
    -0.62
    types
    -0.61
     inval
    -0.60
    monton
    -0.58
     shelters
    -0.58
    die
    -0.58
    gets
    -0.58
    POSITIVE LOGITS
    -.
    0.98
    ohm
    0.94
    00000000
    0.90
    000000
    0.90
    3333
    0.85
    9999
    0.84
    %%
    0.81
    125
    0.80
    %.
    0.79
    Percent
    0.78
    Activations Density 0.044%

    No Known Activations