© 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. 16189
    Prev
    Next
    INDEX
    Explanations

    expressions related to features or specifications, especially related to technology or products

    oai_token-act-pair · gpt-3.5-turbo

    terms related to safety and protection measures

    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
    iddler
    -0.65
     Retrieved
    -0.64
     hijacked
    -0.61
    olor
    -0.60
     corrupted
    -0.57
    cffffcc
    -0.57
    mania
    -0.56
     hysterical
    -0.56
    ulia
    -0.56
     Cra
    -0.56
    POSITIVE LOGITS
     avoids
    1.28
    avoid
    1.22
     avoided
    1.19
     avoid
    1.18
     minimal
    1.11
     minim
    1.10
     no
    1.08
     minimize
    1.06
     minimizing
    1.05
     unaffected
    1.02
    Activations Density 1.354%

    No Known Activations