© 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. 2-RES-JB
    11. 4400
    Prev
    Next
    INDEX
    Explanations

    keywords related to news headlines and notable individuals

    oai_token-act-pair · gpt-3.5-turbo

    phrases that begin with "There" indicating existence or occurrence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CJ
    -0.77
     actionGroup
    -0.74
     pound
    -0.72
     ±
    -0.70
     micro
    -0.69
     digest
    -0.68
     ed
    -0.65
     beans
    -0.64
     feet
    -0.63
     dairy
    -0.62
    POSITIVE LOGITS
    abouts
    1.23
    upon
    0.96
    ngth
    0.95
    ntil
    0.94
     fortun
    0.93
    ilst
    0.85
    olkien
    0.82
    GoldMagikarp
    0.81
    hovah
    0.81
    wegian
    0.79
    Activations Density 0.053%

    No Known Activations