© 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. 12953
    Prev
    Next
    INDEX
    Explanations

    instances of numbers accompanied by certain keywords or phrases

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the number 48

    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
    ovie
    -0.78
    bard
    -0.74
    bub
    -0.71
    ilic
    -0.70
     Pros
    -0.70
    andise
    -0.68
    ugu
    -0.68
    rison
    -0.68
    folios
    -0.68
    apego
    -0.66
    POSITIVE LOGITS
    576
    1.07
    eenth
    0.91
    MJ
    0.87
    kHz
    0.82
    een
    0.82
     Hours
    0.80
     cents
    0.80
    terness
    0.79
    80
    0.79
    ©¶æ¥µ
    0.77
    Activations Density 0.034%

    No Known Activations