© 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. 4-RES-JB
    11. 3647
    Prev
    Next
    INDEX
    Explanations

    words related to negativity or disgrace

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases indicating moral judgment or condemnation

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

    No Comments

    Negative Logits
    ħĭ
    -0.74
     Leilan
    -0.69
    king
    -0.65
    izoph
    -0.63
    stood
    -0.62
     Immunity
    -0.60
    plane
    -0.60
    wan
    -0.59
    draw
    -0.58
    llan
    -0.58
    POSITIVE LOGITS
    ations
    1.21
    omin
    1.21
    atory
    1.05
    ational
    0.99
    ious
    0.96
    ifer
    0.96
    ator
    0.96
    itives
    0.93
    omial
    0.93
    atus
    0.93
    Activations Density 0.019%

    No Known Activations