Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 2501
    Prev
    Next
    INDEX
    Explanations

    phrases related to poor quality or performance

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ategory
    -0.84
    ubi
    -0.81
    SPONSORED
    -0.80
    Pi
    -0.77
    Ru
    -0.68
    irs
    -0.67
    ":[
    -0.66
     {:
    -0.66
    pta
    -0.66
    CU
    -0.66
    POSITIVE LOGITS
     quality
    1.15
     hygiene
    1.11
     judgement
    0.98
     luck
    0.96
     manners
    0.95
     imitation
    0.94
     digestion
    0.91
     performers
    0.91
     judgment
    0.90
    quality
    0.90
    Activations Density 0.064%

    No Known Activations