© 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. 11-RES-JB
    11. 18744
    Prev
    Next
    INDEX
    Explanations

    mentions of reviews or summaries of various types of visual media

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to announcements or recommendations

    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
    paren
    -0.73
     disadvant
    -0.71
     usefulness
    -0.69
    RFC
    -0.66
     Solutions
    -0.64
    hemat
    -0.63
    Anonymous
    -0.63
    Abstract
    -0.62
    igslist
    -0.62
     euth
    -0.61
    POSITIVE LOGITS
     spoil
    0.89
     spoilers
    0.87
     teaser
    0.86
     spoiler
    0.84
     trailer
    0.84
     preview
    0.82
    tainment
    0.82
     synopsis
    0.80
     previews
    0.80
     exclusively
    0.79
    Activations Density 0.364%

    No Known Activations