© 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. 9-RES-JB
    11. 18577
    Prev
    Next
    INDEX
    Explanations

    numbers and quantities

    oai_token-act-pair · gpt-3.5-turbo

    numerical data related to statistics and quantifiable information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    angelo
    -0.64
     nutshell
    -0.63
    cking
    -0.57
     whipping
    -0.55
     whirlwind
    -0.55
    dayName
    -0.55
    uyomi
    -0.54
    00200000
    -0.54
     Stamp
    -0.54
    tnc
    -0.53
    POSITIVE LOGITS
     were
    1.15
     survived
    1.09
     are
    1.09
     succumbed
    1.08
     died
    1.07
     went
    1.06
     withdrew
    1.04
     perished
    1.03
     stayed
    1.01
     belonged
    0.96
    Activations Density 0.242%

    No Known Activations