© 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. 17238
    Prev
    Next
    INDEX
    Explanations

    mentions related to brand identity and marketing

    oai_token-act-pair · gpt-3.5-turbo

    references to products or services and their attributes in commercial contexts

    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
    backs
    -0.71
    etsk
    -0.65
    ays
    -0.64
    ricanes
    -0.62
    uel
    -0.60
    scrib
    -0.60
    atives
    -0.59
    iddles
    -0.59
    irens
    -0.59
     Cob
    -0.58
    POSITIVE LOGITS
     circumstance
    1.20
     denomination
    1.18
     organization
    1.17
     institution
    1.16
     genre
    1.15
     organisation
    1.15
     entity
    1.14
     locale
    1.11
     locality
    1.10
     person
    1.08
    Activations Density 0.256%

    No Known Activations