© 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. 0-RES-JB
    11. 11630
    Prev
    Next
    INDEX
    Explanations

    comments sections

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "comments" and variations of the word "honesty."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ashington
    -0.70
    itle
    -0.68
    asure
    -0.67
    å°Ĩ
    -0.67
    EGIN
    -0.67
     Nev
    -0.65
    trump
    -0.65
    gon
    -0.65
    opt
    -0.62
     presidents
    -0.61
    POSITIVE LOGITS
     Comments
    1.76
    esty
    1.64
     Forms
    1.62
     Cookies
    1.32
     Views
    1.15
     squid
    1.06
    Blog
    0.86
     Flowers
    0.85
    xual
    0.79
    ĸļ
    0.76
    Activations Density 0.027%

    No Known Activations