© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 4834
    Prev
    Next
    INDEX
    Explanations

    references to official statements or publications made on websites

    oai_token-act-pair · gpt-3.5-turbo

    instances of statements or posts made online, especially those associated with specific dates or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gage
    -0.82
    CEPT
    -0.73
     =>
    -0.70
    OIL
    -0.65
    Gs
    -0.64
     duct
    -0.63
    tin
    -0.63
    tested
    -0.63
     sidx
    -0.63
    SAY
    -0.62
    POSITIVE LOGITS
     behalf
    0.87
    tained
    0.68
     paras
    0.68
     launch
    0.66
     Melody
    0.66
     Deadline
    0.66
     Wired
    0.65
     HuffPost
    0.65
     Fortune
    0.65
     announcing
    0.65
    Activations Density 0.263%

    No Known Activations