© 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. 20618
    Prev
    Next
    INDEX
    Explanations

    mentions of specific numbers or codes

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to economic and legal topics

    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
     destiny
    -0.51
     mosqu
    -0.49
     unemploy
    -0.46
     weddings
    -0.43
     patronage
    -0.43
     infringing
    -0.43
    ModLoader
    -0.43
     transsexual
    -0.42
     interchangeable
    -0.42
     guiActiveUn
    -0.42
    POSITIVE LOGITS
    ĺ
    0.54
    ade
    0.54
    end
    0.52
    eal
    0.52
    ©
    0.50
    ends
    0.50
    £
    0.50
    ense
    0.49
    anse
    0.49
    ty
    0.49
    Activations Density 0.897%

    No Known Activations