Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 2770
    Prev
    Next
    INDEX
    Explanations

    advertisements marked by special characters

    oai_token-act-pair · gpt-3.5-turbo

    repeated phrases or structures, particularly in the context of advertisements or directives

    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
     advoc
    -0.93
     neighb
    -0.84
     princ
    -0.82
     mathemat
    -0.80
     citiz
    -0.78
     unification
    -0.76
     perspect
    -0.76
     embark
    -0.75
     flavours
    -0.75
     unreal
    -0.74
    POSITIVE LOGITS
    Advertisement
    2.50
    Alert
    1.74
    RELATED
    1.56
    MORE
    1.54
    advertisement
    1.47
    Photo
    1.25
    SPONSORED
    1.22
    Getty
    1.21
    Newsletter
    1.20
    Spons
    1.19
    Activations Density 0.059%

    No Known Activations