© 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. 6-RES-JB
    11. 12283
    Prev
    Next
    INDEX
    Explanations

    numerical values containing the word "pent"

    oai_token-act-pair · gpt-3.5-turbo

    references to "pent" or associated terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãģĦ
    -0.74
    士
    -0.71
    ISSION
    -0.68
     Referred
    -0.68
    OAD
    -0.67
    pedia
    -0.65
    BILITY
    -0.65
     Mahar
    -0.65
     Milo
    -0.64
     Lima
    -0.63
    POSITIVE LOGITS
    agon
    1.13
     pent
    1.05
    agons
    1.02
    iple
    1.01
    etr
    1.00
    inct
    0.99
    acle
    0.94
    acles
    0.93
    raph
    0.92
    agram
    0.91
    Activations Density 0.022%

    No Known Activations