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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 23382
    Prev
    Next
    INDEX
    Explanations

    mentions of violent or emotionally intense events

    oai_token-act-pair · gpt-3.5-turbo

    references to political events or conditions

    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
     1978
    -0.67
     1980
    -0.66
     1966
    -0.63
    assetsadobe
    -0.62
     1977
    -0.62
    ĸļ
    -0.61
     wartime
    -0.61
     1981
    -0.61
     1969
    -0.60
     1976
    -0.60
    POSITIVE LOGITS
    âĢ
    1.09
    âĺ
    0.95
    âĶ
    0.95
    ðŁij
    0.89
    âĨ
    0.89
     âĢ
    0.87
    âĻ
    0.86
    âĿ
    0.85
    âľ
    0.83
    ðŁ
    0.81
    Activations Density 1.224%

    No Known Activations