© 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. 8-RES-JB
    11. 4607
    Prev
    Next
    INDEX
    Explanations

    phrases related to strong disapproval or criticism

    oai_token-act-pair · gpt-3.5-turbo

    instances of condemnation or denouncement of actions or events

    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
    ramid
    -0.81
    IER
    -0.70
     membr
    -0.68
     Wonders
    -0.68
    emis
    -0.66
    BLIC
    -0.65
    seed
    -0.63
    icle
    -0.63
    NetMessage
    -0.62
    aldo
    -0.62
    POSITIVE LOGITS
     condemn
    0.90
     homophobic
    0.83
     unequivocally
    0.82
    ations
    0.79
     atrocities
    0.79
     condemning
    0.79
     harshly
    0.75
     condemnation
    0.75
    ifiable
    0.75
    urous
    0.75
    Activations Density 0.055%

    No Known Activations