© 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. 8-RES-JB
    11. 3101
    Prev
    Next
    INDEX
    Explanations

    phrases related to recommending or encouraging specific actions or behaviors

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of "the same" and concepts of doing the "right thing."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    quished
    -0.73
    gat
    -0.72
    osponsors
    -0.70
    ildo
    -0.69
    ONSORED
    -0.68
    ospons
    -0.68
    raltar
    -0.66
    urated
    -0.66
     Leilan
    -0.65
    opened
    -0.63
    POSITIVE LOGITS
     same
    1.36
     unthinkable
    1.12
     utmost
    1.09
     slightest
    1.09
     simplest
    1.08
     latter
    1.00
     hardest
    1.00
    same
    0.98
     groundwork
    0.98
     opposite
    0.97
    Activations Density 0.085%

    No Known Activations