© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RES-JB
    11. 23868
    Prev
    Next
    INDEX
    Explanations

    words related to "reports of" something

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating multiple reports or allegations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uristic
    -0.89
    heses
    -0.82
    sters
    -0.81
    hesis
    -0.79
    minus
    -0.76
    ertodd
    -0.74
    keys
    -0.74
    alez
    -0.73
    ards
    -0.72
    nets
    -0.71
    POSITIVE LOGITS
     wrongdoing
    1.10
     inacc
    1.02
     impending
    0.96
     vandalism
    0.94
     persecution
    0.93
     misconduct
    0.93
     harassment
    0.93
     discrimination
    0.90
     contamination
    0.90
     widespread
    0.89
    Activations Density 0.142%

    No Known Activations