© 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. 11562
    Prev
    Next
    INDEX
    Explanations

    words related to topics or themes being focused on or covered in a discussion, review, or analysis

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to examining topics or issues in depth

    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
     collaborator
    -0.66
     Sabha
    -0.66
    lime
    -0.64
    nown
    -0.64
    Sport
    -0.63
    Jar
    -0.62
    ãĥ¼ãĥ«
    -0.61
     rejoice
    -0.61
    lon
    -0.60
    LI
    -0.59
    POSITIVE LOGITS
     topics
    0.76
     pacing
    0.67
     topical
    0.67
     specifics
    0.65
     how
    0.62
     issues
    0.62
     technical
    0.61
     aspects
    0.61
    Merit
    0.59
    ancy
    0.58
    Activations Density 0.207%

    No Known Activations