© 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. 11-RES-JB
    11. 7104
    Prev
    Next
    INDEX
    Explanations

    sentences with impactful statements or global implications

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     guy
    -0.83
     asshole
    -0.82
     buddies
    -0.81
     glim
    -0.79
     toss
    -0.76
     yell
    -0.75
     sergeant
    -0.74
     stuff
    -0.74
     nicer
    -0.74
     pals
    -0.73
    POSITIVE LOGITS
     Therefore
    1.28
     Whilst
    1.27
    Therefore
    1.27
     Consequently
    1.26
     Countries
    1.21
     Recent
    1.20
     Approximately
    1.19
     Currently
    1.19
    Incre
    1.17
     Increasing
    1.16
    Activations Density 0.531%

    No Known Activations