Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 9-RES-JB
    6. 21137
    Prev
    Next
    INDEX
    Explanations

    phrases indicating progress or advancement

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating progress or continuation of actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     teasp
    -0.74
    icious
    -0.72
     countered
    -0.71
    eps
    -0.71
    orah
    -0.69
    unes
    -0.69
    ulhu
    -0.68
    ened
    -0.67
    pecially
    -0.67
    ashington
    -0.66
    POSITIVE LOGITS
     regards
    0.96
    draw
    0.91
     plans
    0.87
     preparations
    0.86
     caution
    0.85
     regard
    0.82
     experimentation
    0.77
     whatever
    0.76
     renovations
    0.75
     precaution
    0.74
    Activations Density 0.059%

    No Known Activations