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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 6-RES-JB
    6. 18401
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to locations or entities with numbers or counting elements in them

    oai_token-act-pair · gpt-3.5-turbo

    mentions of numbers and numerical references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     includ
    -0.75
    inating
    -0.69
    yrim
    -0.66
    ushes
    -0.65
    ained
    -0.64
    vt
    -0.64
    USD
    -0.64
    activity
    -0.64
    adel
    -0.64
     clock
    -0.63
    POSITIVE LOGITS
    teen
    1.05
     Hundred
    1.01
     Mile
    0.96
     Eye
    0.93
     Thousand
    0.92
     Lives
    0.92
     Isles
    0.89
    een
    0.87
     Vision
    0.85
     Eyes
    0.84
    Activations Density 0.051%

    No Known Activations