© 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. 0-RES-JB
    11. 22395
    Prev
    Next
    INDEX
    Explanations

    mentions of organizations, especially international ones

    oai_token-act-pair · gpt-3.5-turbo

    references to various organizations, particularly health-related ones

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cris
    -0.68
     thrill
    -0.67
     hindsight
    -0.65
     beam
    -0.65
     deer
    -0.63
     fuzz
    -0.63
    bly
    -0.63
     ba
    -0.61
     pedal
    -0.60
     dry
    -0.60
    POSITIVE LOGITS
     Organization
    4.15
     Organisation
    3.35
     Organizations
    1.99
     organization
    1.70
     Association
    1.27
    Organ
    1.27
     Organ
    1.23
     organisation
    1.20
     organizations
    1.20
     organizational
    1.20
    Activations Density 0.013%

    No Known Activations