© 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. 3-RES-JB
    11. 15045
    Prev
    Next
    INDEX
    Explanations

    terms indicating close observation or monitoring

    oai_token-act-pair · gpt-3.5-turbo

    references to careful observation or scrutiny

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ICAN
    -0.83
     Bucket
    -0.72
     Chaser
    -0.72
    ule
    -0.66
     Lightning
    -0.66
     Memories
    -0.65
    æĹ
    -0.65
     Mania
    -0.65
     Bronze
    -0.64
    IRO
    -0.64
    POSITIVE LOGITS
     aligned
    0.95
     resembles
    0.90
     closely
    0.86
     scrutin
    0.83
     resemble
    0.82
     enough
    0.82
    wired
    0.81
     minded
    0.80
     resembled
    0.80
     correlated
    0.79
    Activations Density 0.009%

    No Known Activations