© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 20360
    Prev
    Next
    INDEX
    Explanations

    mentions of the country "German" or things related to Germany

    oai_token-act-pair · gpt-3.5-turbo

    references to Germany and German-related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ciating
    -0.95
    ctica
    -0.84
    tis
    -0.83
    vae
    -0.82
    efeated
    -0.79
    heed
    -0.77
    xus
    -0.76
    okemon
    -0.76
    mble
    -0.75
    lihood
    -0.74
    POSITIVE LOGITS
    wings
    1.07
     Chancellor
    1.07
     shepherd
    0.98
     Bundesliga
    0.89
     Shepherd
    0.88
     Expression
    0.81
     chancellor
    0.80
     Bundes
    0.79
     Ide
    0.78
     Aerospace
    0.77
    Activations Density 0.022%

    No Known Activations