© 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. 5064
    Prev
    Next
    INDEX
    Explanations

    phrases related to proposed actions or decisions

    oai_token-act-pair · gpt-3.5-turbo
    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
     steroids
    -0.72
     dating
    -0.71
     withdrawal
    -0.69
     Ferdinand
    -0.67
     eviction
    -0.64
     brunt
    -0.64
     whereabouts
    -0.64
     displeasure
    -0.63
     charm
    -0.61
     Cent
    -0.60
    POSITIVE LOGITS
    ³³³³³³³³
    1.25
    ³³³³³³³³³³³³³³³³
    1.19
    ³³³³
    1.09
    ³³³
    1.06
    "âĢ¦
    0.99
    "...
    0.99
    Liter
    0.88
    اÙĦ
    0.87
    Certain
    0.86
    "[
    0.81
    Activations Density 0.102%

    No Known Activations