© 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. 4-RES-JB
    11. 10185
    Prev
    Next
    INDEX
    Explanations

    phrases related to computer systems

    oai_token-act-pair · gpt-3.5-turbo

    references to technological systems or frameworks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tein
    -0.74
    ishable
    -0.73
    bow
    -0.73
    hab
    -0.71
    onga
    -0.71
    urous
    -0.70
    liest
    -0.69
    azo
    -0.68
    rica
    -0.68
    iary
    -0.67
    POSITIVE LOGITS
    atics
    1.00
    atically
    0.89
     integ
    0.88
     systems
    0.87
    ycle
    0.84
     tray
    0.83
    atic
    0.83
    ctl
    0.80
     system
    0.78
     administrators
    0.77
    Activations Density 0.039%

    No Known Activations