© 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. 1-RES-JB
    11. 13462
    Prev
    Next
    INDEX
    Explanations

    words related to rapid increase or decrease in intensity or amount

    oai_token-act-pair · gpt-3.5-turbo

    verbs and phrases that indicate decline or negative change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CLSID
    -0.80
    ©¶æ
    -0.74
    anooga
    -0.73
    gemony
    -0.68
    iciency
    -0.68
    abet
    -0.66
    cill
    -0.66
     Expression
    -0.65
    emark
    -0.65
    ses
    -0.64
    POSITIVE LOGITS
    hower
    0.93
     downhill
    0.81
    staking
    0.81
     earthqu
    0.78
    interstitial
    0.78
    cycles
    0.75
     economies
    0.71
     tides
    0.71
     peaks
    0.71
    nir
    0.70
    Activations Density 0.282%

    No Known Activations