© 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. 10-RES-JB
    11. 12787
    Prev
    Next
    INDEX
    Explanations

    phone-related actions and tech terms

    oai_token-act-pair · gpt-3.5-turbo

    references to mobile devices and their applications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    OIL
    -0.92
     Letters
    -0.75
     ordinances
    -0.74
     bonuses
    -0.72
     bids
    -0.69
     Breed
    -0.69
     inspections
    -0.69
    escription
    -0.67
    steen
    -0.66
     abortions
    -0.66
    POSITIVE LOGITS
     smartphone
    1.51
     laptop
    1.49
     tablet
    1.42
     iPad
    1.40
     desktop
    1.38
     smartphones
    1.38
     touchscreen
    1.34
     Chromebook
    1.34
     device
    1.33
     handheld
    1.32
    Activations Density 0.252%

    No Known Activations