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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 8-RES-JB
    11. 7214
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly related to locations and names

    oai_token-act-pair · gpt-3.5-turbo

    references to numerical information or data points

    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
    Analy
    -0.68
    anything
    -0.67
    Unknown
    -0.65
     causation
    -0.61
    entimes
    -0.60
    limits
    -0.60
     timely
    -0.56
     tempting
    -0.56
    ctica
    -0.56
     appetite
    -0.56
    POSITIVE LOGITS
     Blvd
    1.06
     Ave
    0.88
     Rd
    0.85
     acres
    0.78
    illion
    0.76
    âĦ¢:
    0.66
    "]=>
    0.65
     Parade
    0.64
    estamp
    0.64
    士
    0.64
    Activations Density 0.511%

    No Known Activations