© 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. 2-RES-JB
    11. 350
    Prev
    Next
    INDEX
    Explanations

    words denoting a person who has been harmed or injured, particularly in the context of a crime or wrongdoing

    oai_token-act-pair · gpt-4-turbo

    words related to victimization or legal proceedings

    oai_token-act-pair · gpt-3.5-turbo

    references to victims in various contexts

    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
    andel
    -0.84
    aeda
    -0.74
    ooks
    -0.71
    rosso
    -0.70
    hire
    -0.69
    leaf
    -0.68
    ort
    -0.66
    obar
    -0.64
    lav
    -0.64
    upp
    -0.63
    POSITIVE LOGITS
     Victims
    0.96
     victim
    0.93
    izers
    0.92
     victims
    0.92
     Victim
    0.91
    izes
    0.91
    vict
    0.86
    Vict
    0.85
    hood
    0.84
    izer
    0.82
    Activations Density 0.017%

    No Known Activations