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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 16359
    Prev
    Next
    INDEX
    Explanations

    names of notable individuals or institutions

    oai_token-act-pair · gpt-3.5-turbo

    references to formal events and official proceedings

    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
    channelAvailability
    -0.65
    }}}
    -0.55
     vulner
    -0.54
    nant
    -0.54
    default
    -0.52
    ITED
    -0.50
    odynam
    -0.49
    Loading
    -0.49
    wd
    -0.47
    agra
    -0.47
    POSITIVE LOGITS
     that
    1.47
    that
    1.36
     THAT
    1.03
    That
    0.97
     That
    0.95
     how
    0.82
    ]:
    0.74
     why
    0.70
    è¦ļéĨĴ
    0.70
    :
    0.68
    Activations Density 0.323%

    No Known Activations