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. 13038
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal identity and self-discovery

    oai_token-act-pair · gpt-3.5-turbo

    connections and relationships in personal narratives

    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
    rique
    -0.95
    rers
    -0.80
    visors
    -0.71
    onde
    -0.69
    tyard
    -0.68
    asio
    -0.67
    §
    -0.67
     reopened
    -0.65
    osures
    -0.65
     fronts
    -0.65
    POSITIVE LOGITS
     viz
    0.82
    Magikarp
    0.82
     namely
    0.79
    whether
    0.77
     THEN
    0.75
    etc
    0.74
     determines
    0.74
     subtract
    0.71
    BUT
    0.68
    Tokens
    0.68
    Activations Density 0.449%

    No Known Activations