© 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. 6-RES-JB
    11. 18789
    Prev
    Next
    INDEX
    Explanations

    verbs and phrases indicating future actions or potential outcomes

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating future potential or outcomes

    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
    Tips
    -0.63
    Trivia
    -0.58
    ockets
    -0.56
    bara
    -0.54
    ressing
    -0.54
    onsense
    -0.54
    zbollah
    -0.53
     Hib
    -0.53
    outside
    -0.53
    rescent
    -0.53
    POSITIVE LOGITS
     someday
    0.79
     be
    0.78
     likely
    0.76
     soon
    0.76
     beh
    0.76
    ãĥ¼ãĥ
    0.74
     eventually
    0.71
     hereafter
    0.69
    ãĥ¼ãĥĨãĤ£
    0.68
     Benefit
    0.67
    Activations Density 0.327%

    No Known Activations