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. 6-RES-JB
    6. 5507
    Prev
    Next
    INDEX
    Explanations

    text related to imaging techniques and data analysis

    oai_token-act-pair · gpt-3.5-turbo

    scientific terms and phrases related to imaging or imaging techniques

    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
    rather
    -0.69
     rather
    -0.56
    ãģĻ
    -0.53
    aly
    -0.52
    abetes
    -0.52
    opa
    -0.52
    Interstitial
    -0.51
    instead
    -0.51
    zi
    -0.50
    oji
    -0.50
    POSITIVE LOGITS
     awaits
    0.83
     meanwhile
    0.81
     consists
    0.74
     ensued
    0.72
     flowed
    0.71
     appeared
    0.70
     consisted
    0.70
     hangs
    0.70
     exists
    0.69
     arrived
    0.68
    Activations Density 1.036%

    No Known Activations