© 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. 6466
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to various companies, bands, or organizations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of company names and associated brand elements

    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
     awa
    -0.91
     hump
    -0.76
     drought
    -0.74
     proble
    -0.74
     shortage
    -0.74
     stroke
    -0.73
     specially
    -0.73
     costly
    -0.72
     barred
    -0.71
     charged
    -0.71
    POSITIVE LOGITS
     Productions
    1.25
     Studios
    1.24
    Stud
    1.17
    Gaming
    1.16
     Labs
    1.13
     Entertainment
    1.12
    Games
    1.04
     Robotics
    1.03
    HQ
    1.03
     Collective
    1.02
    Activations Density 0.419%

    No Known Activations