© 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. 1-RES-JB
    11. 8020
    Prev
    Next
    INDEX
    Explanations

    names or terms related to a person named Barry

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Garry" and variations of it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    STD
    -0.74
    VD
    -0.67
     CLSID
    -0.66
     crawl
    -0.65
    ĺħ
    -0.64
     consolation
    -0.64
    DOC
    -0.61
    umers
    -0.60
    Fal
    -0.60
    ixed
    -0.59
    POSITIVE LOGITS
    arry
    1.18
    theless
    1.01
    ments
    0.88
    ing
    0.83
    ás
    0.83
    tainment
    0.79
    lene
    0.74
    ards
    0.73
    rette
    0.72
    reys
    0.71
    Activations Density 0.007%

    No Known Activations