© 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. 8-RES-JB
    11. 741
    Prev
    Next
    INDEX
    Explanations

    names of companies and individuals

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, especially names of people and locations

    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
    escription
    -0.81
    etheless
    -0.77
    someone
    -0.74
    inventoryQuantity
    -0.72
    emort
    -0.71
    agonists
    -0.71
    ccording
    -0.68
     Adin
    -0.67
    20439
    -0.67
     referen
    -0.65
    POSITIVE LOGITS
     LLP
    1.58
     Ltd
    1.36
     Associates
    1.22
     Productions
    1.21
     Resort
    1.19
     Architects
    1.18
     LLC
    1.13
     Hospital
    1.13
     Enterprises
    1.12
     Company
    1.11
    Activations Density 0.438%

    No Known Activations