© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 4056
    Prev
    Next
    INDEX
    Explanations

    phrases related to technology updates and releases

    oai_token-act-pair · gpt-3.5-turbo

    periods at the end of sentences

    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
     allowance
    -0.77
     enrol
    -0.76
     literacy
    -0.75
     defe
    -0.74
     reflex
    -0.73
     imperson
    -0.73
     scourge
    -0.72
     cellar
    -0.71
     smallest
    -0.70
    ling
    -0.70
    POSITIVE LOGITS
     Additionally
    1.17
    Downloadha
    1.15
     However
    1.13
     Meanwhile
    1.10
     Unfortunately
    1.08
     Notably
    1.05
     Currently
    1.05
     Furthermore
    1.04
     Previously
    1.04
     Whereas
    1.03
    Activations Density 0.944%

    No Known Activations