© 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. 9911
    Prev
    Next
    INDEX
    Explanations

    phrases related to embedding information or content within something else

    oai_token-act-pair · gpt-3.5-turbo

    terms related to embedding or being embedded within a context

    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
    wagen
    -0.71
     comprehens
    -0.67
    gers
    -0.63
     obsc
    -0.61
     partial
    -0.59
    pmwiki
    -0.59
     wolves
    -0.58
     è£ı
    -0.58
     speakers
    -0.58
    ãĤŃ
    -0.58
    POSITIVE LOGITS
    arrass
    1.54
    edded
    1.52
    odied
    1.38
    argo
    1.26
    assies
    1.25
    assy
    1.23
    attled
    1.21
    assador
    1.10
    ree
    1.07
    edd
    1.05
    Activations Density 0.044%

    No Known Activations