© 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. 11-RES-JB
    11. 10053
    Prev
    Next
    INDEX
    Explanations

    keywords related to reviewing and recommending products or services

    oai_token-act-pair · gpt-3.5-turbo

    components related to product reviews and purchasing decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pand
    -0.76
     contagious
    -0.70
    ongo
    -0.69
     curfew
    -0.69
    externalActionCode
    -0.66
     dementia
    -0.65
     kissed
    -0.64
     Yiannopoulos
    -0.64
     sprinkled
    -0.64
     disrupted
    -0.64
    POSITIVE LOGITS
     Manufacturer
    1.52
     warranty
    1.41
     Specifications
    1.35
     specs
    1.35
     Warranty
    1.33
     manufacturer
    1.30
     datas
    1.29
     manufactures
    1.26
    Manufact
    1.25
     OEM
    1.23
    Activations Density 0.549%

    No Known Activations