© 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. 10-RES-JB
    11. 20409
    Prev
    Next
    INDEX
    Explanations

    mixed statements with opinions and observations

    oai_token-act-pair · gpt-3.5-turbo

    references to emotional or mental states of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    otine
    -0.62
     spokeswoman
    -0.57
    %%
    -0.55
    ackets
    -0.53
    sonian
    -0.51
     jurisd
    -0.51
    arest
    -0.51
    stadt
    -0.50
    PDF
    -0.50
    roups
    -0.49
    POSITIVE LOGITS
     he
    1.95
    He
    1.86
    His
    1.85
    his
    1.80
     his
    1.79
     He
    1.67
     His
    1.58
     himself
    1.46
    he
    1.42
     HIS
    1.30
    Activations Density 0.909%

    No Known Activations