© 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. 597
    Prev
    Next
    INDEX
    Explanations

    verbs denoting the act of addition or incorporation

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate the concept of addition or accumulation

    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
    irection
    -0.81
    pires
    -0.62
    avior
    -0.61
    cember
    -0.59
    jan
    -0.58
    aviour
    -0.57
     exits
    -0.57
    adem
    -0.57
     PART
    -0.56
     reprinted
    -0.55
    POSITIVE LOGITS
     pile
    0.94
     woes
    0.83
     intrigue
    0.80
     repertoire
    0.78
     already
    0.77
     list
    0.76
     existing
    0.76
     complicate
    0.76
     coffers
    0.75
     mix
    0.74
    Activations Density 0.130%

    No Known Activations