© 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. 6292
    Prev
    Next
    INDEX
    Explanations

    mentions of vegetarianism

    oai_token-act-pair · gpt-3.5-turbo

    references to vegetarianism and related concepts

    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
     immersion
    -0.76
     deposition
    -0.73
     skelet
    -0.71
    ather
    -0.70
    sembly
    -0.68
     rich
    -0.66
     periphery
    -0.66
     coffin
    -0.66
    ĸļ
    -0.65
     death
    -0.65
    POSITIVE LOGITS
    cies
    0.83
    MENTS
    0.74
    ilan
    0.73
    okemon
    0.71
    TION
    0.70
     è£ıè
    0.69
    \">
    0.68
     Gat
    0.66
    oles
    0.66
    ooks
    0.66
    Activations Density 0.000%

    No Known Activations