© 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. 2-RES-JB
    11. 8356
    Prev
    Next
    INDEX
    Explanations

    words related to various forms and aspects of oppression

    oai_token-act-pair · gpt-3.5-turbo

    terms related to oppression and marginalized groups

    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
    WAYS
    -0.77
    tein
    -0.70
    cigarettes
    -0.70
    cephal
    -0.68
    Dub
    -0.67
    PET
    -0.67
    Lew
    -0.65
    uchin
    -0.65
    SEE
    -0.64
    sal
    -0.64
    POSITIVE LOGITS
     oppression
    1.04
     oppress
    1.03
     oppressed
    0.88
     disadvant
    0.82
    retched
    0.79
     Struggle
    0.76
     injust
    0.74
     Palest
    0.74
     oppressive
    0.72
     injustice
    0.72
    Activations Density 0.016%

    No Known Activations