© 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. 8-RES-JB
    6. 20053
    Prev
    Next
    INDEX
    Explanations

    words related to mistreatment or error

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "mist" and its variations, indicating themes of errors or malpractices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    phrine
    -0.65
     scratch
    -0.65
    brate
    -0.63
    Interstitial
    -0.62
    mits
    -0.62
    CLUS
    -0.61
    jriwal
    -0.61
    Reviewer
    -0.61
    lishes
    -0.61
    */(
    -0.60
    POSITIVE LOGITS
    reatment
    1.52
    reated
    1.33
    rans
    1.16
    ypes
    1.16
    reating
    1.16
    arget
    1.05
    resses
    1.02
    reat
    1.00
    mallow
    1.00
    aken
    1.00
    Activations Density 0.018%

    No Known Activations