© 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. 9-RES-JB
    11. 22688
    Prev
    Next
    INDEX
    Explanations

    terms related to dates and university names

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to interference in technology and communication contexts

    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
    sic
    -0.69
    etheless
    -0.68
    ospons
    -0.67
    them
    -0.67
    vertisement
    -0.66
     pione
    -0.66
    Ě
    -0.66
    ù
    -0.66
    embedreportprint
    -0.65
    ü
    -0.65
    POSITIVE LOGITS
     hampered
    0.52
     losers
    0.52
     vain
    0.52
     favourites
    0.51
     slump
    0.50
     Jagu
    0.50
     redund
    0.50
     Restaur
    0.49
     stagnation
    0.49
     blues
    0.49
    Activations Density 1.706%

    No Known Activations