© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 8-RES-JB
    11. 4299
    Prev
    Next
    INDEX
    Explanations

    references to specific titles and names within various contexts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to activism, events, and notable products or themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    theless
    -0.79
    omever
    -0.76
    IDA
    -0.68
     comprom
    -0.65
     lowly
    -0.64
     pend
    -0.63
     tune
    -0.63
     tide
    -0.62
    terday
    -0.61
     Colomb
    -0.60
    POSITIVE LOGITS
     Released
    0.82
    itars
    0.81
     Profile
    0.81
    ounces
    0.79
     Facts
    0.77
     Rankings
    0.76
     Joined
    0.75
     Casting
    0.75
     Edition
    0.75
     Tracks
    0.74
    Activations Density 0.380%

    No Known Activations