© 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. 10034
    Prev
    Next
    INDEX
    Explanations

    words related to social, political, or economic topics

    oai_token-act-pair · gpt-3.5-turbo

    references to significant societal challenges or 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
    onz
    -0.84
    ramids
    -0.81
    DOS
    -0.77
    amaz
    -0.73
    ãĥīãĥ©
    -0.71
    Recipe
    -0.70
    sis
    -0.67
    hran
    -0.66
    pse
    -0.66
    arus
    -0.65
    POSITIVE LOGITS
     affecting
    1.29
     pertaining
    1.24
     impacting
    1.16
     relating
    1.14
     raised
    1.10
     facing
    1.10
     concerning
    1.09
     confronting
    1.06
     arising
    1.06
     pertinent
    1.05
    Activations Density 0.110%

    No Known Activations