© 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. 23877
    Prev
    Next
    INDEX
    Explanations

    terms related to fields of study, governmental organizations, and locations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to social and political structures

    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
     innocence
    -0.67
     peac
    -0.64
     onlook
    -0.56
    iour
    -0.55
     suspic
    -0.54
     craz
    -0.53
     skim
    -0.51
     strang
    -0.51
     stal
    -0.51
     lif
    -0.50
    POSITIVE LOGITS
     ):
    0.90
    ;;;;;;;;;;;;
    0.88
    =-=-=-=-
    0.85
    ");
    0.84
     ).
    0.83
     RELEASE
    0.82
     Includes
    0.81
    "),
    0.81
     Written
    0.79
    ").
    0.79
    Activations Density 0.450%

    No Known Activations