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. 11-RES-JB
    6. 17877
    Prev
    Next
    INDEX
    Explanations

    concerns expressed about various issues or topics

    oai_token-act-pair · gpt-3.5-turbo

    expressions of concern regarding various issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DragonMagazine
    -1.01
    rete
    -0.84
    MX
    -0.80
    OGR
    -0.80
    ession
    -0.75
    orld
    -0.75
    NES
    -0.75
    ectomy
    -0.74
    xxxxxxxx
    -0.71
    istics
    -0.70
    POSITIVE LOGITS
     whether
    1.12
     repercussions
    1.12
     losing
    1.06
     possible
    1.04
     potential
    0.99
     heights
    0.99
     impending
    0.98
     how
    0.97
     dangers
    0.97
     safety
    0.97
    Activations Density 0.124%

    No Known Activations