© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 12798
    Prev
    Next
    INDEX
    Explanations

    mentions of various forms of harassment

    oai_token-act-pair · gpt-3.5-turbo

    instances of harassment-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éĹĺ
    -0.83
    zyme
    -0.76
    stanbul
    -0.76
    ECD
    -0.75
    rians
    -0.72
    ACTED
    -0.69
    inet
    -0.69
    rient
    -0.69
    sonian
    -0.68
    kos
    -0.68
    POSITIVE LOGITS
     harassment
    1.02
     harass
    0.90
     harassing
    0.83
     tactics
    0.82
    assment
    0.81
     accus
    0.81
     stalking
    0.80
     harassed
    0.76
     allegations
    0.74
     inflic
    0.74
    Activations Density 0.022%

    No Known Activations