© 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. 11-RES-JB
    11. 18604
    Prev
    Next
    INDEX
    Explanations

    phrases related to locations or places

    oai_token-act-pair · gpt-3.5-turbo

    key terms related to governance and political institutions

    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
    »Ĵ
    -0.79
    odied
    -0.71
    ģĸ
    -0.69
    actionDate
    -0.68
    until
    -0.68
    Sem
    -0.66
    tml
    -0.65
    rones
    -0.64
    ãĤ¨ãĥ«
    -0.63
    irlf
    -0.63
    POSITIVE LOGITS
    's
    1.19
     inability
    1.11
     unwillingness
    1.10
     being
    1.09
     reluctance
    1.09
     refusal
    1.03
     having
    1.02
     inaction
    1.02
     penchant
    1.00
     seeming
    1.00
    Activations Density 0.592%

    No Known Activations