© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 15344
    Prev
    Next
    INDEX
    Explanations

    phrases related to large numbers or quantities

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a large quantity or number of people or entities

    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
    avior
    -0.81
    terms
    -0.74
    _>
    -0.71
    dict
    -0.68
    ester
    -0.68
    Dialogue
    -0.68
    otiation
    -0.68
    Discuss
    -0.68
    System
    -0.68
    Fram
    -0.67
    POSITIVE LOGITS
     pounds
    1.12
     miles
    1.10
     dollars
    1.10
     thousands
    1.07
     acres
    1.06
     kilometres
    1.02
     kilometers
    0.99
     hectares
    0.98
     kilograms
    0.95
     pages
    0.91
    Activations Density 0.083%

    No Known Activations