© 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. 3-RES-JB
    11. 2833
    Prev
    Next
    INDEX
    Explanations

    phrases related to the Chandrayaan mission

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Chandrayaan" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    utenberg
    -0.79
    ãĥ¯
    -0.76
    ITED
    -0.69
    istered
    -0.69
    DOS
    -0.69
    DIT
    -0.68
    PORT
    -0.68
    ocamp
    -0.68
    ccess
    -0.66
    espie
    -0.66
    POSITIVE LOGITS
     Chand
    0.98
    bone
    0.82
    lers
    0.80
    rab
    0.80
    nai
    0.79
    enei
    0.78
    storms
    0.77
    borgh
    0.77
    ronics
    0.73
    washer
    0.70
    Activations Density 0.022%

    No Known Activations