© 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. 974
    Prev
    Next
    INDEX
    Explanations

    words that imply a negative or dishonorable action or attribute

    oai_token-act-pair · gpt-4-turbo

    words related to dishonesty or dishonorable behavior

    oai_token-act-pair · gpt-3.5-turbo

    references to dishonesty and honorable actions, including high-stakes situations and individuals associated with them

    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
    esta
    -0.95
    agy
    -0.82
    isine
    -0.81
    izens
    -0.80
    urgy
    -0.80
    rooms
    -0.76
    heast
    -0.74
    ele
    -0.74
    arian
    -0.73
    icles
    -0.72
    POSITIVE LOGITS
    RECT
    0.79
    CLAIM
    0.77
    é»Ĵ
    0.75
    POSE
    0.75
    BuyableInstoreAndOnline
    0.75
    åĬ
    0.71
    ments
    0.70
     omission
    0.69
    \\\\\\\\\\\\\\\\
    0.69
    OUP
    0.67
    Activations Density 0.033%

    No Known Activations