Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 3097
    Prev
    Next
    INDEX
    Explanations

    descriptive words or phrases indicating quality or characteristics

    oai_token-act-pair · gpt-3.5-turbo

    statements that describe the nature or characteristics of various subjects

    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
    inus
    -0.84
    uld
    -0.80
     Discussion
    -0.75
    enary
    -0.74
     Needs
    -0.74
    iatus
    -0.73
     Anniversary
    -0.73
     NOTE
    -0.72
    inav
    -0.72
     Supports
    -0.71
    POSITIVE LOGITS
     undeniably
    1.16
     unmist
    1.12
     emblem
    1.12
     downright
    1.10
     exqu
    1.06
     reminiscent
    1.06
     strikingly
    1.06
     indistinguishable
    1.04
     remarkably
    1.04
     invariably
    1.03
    Activations Density 0.343%

    No Known Activations