© 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. 4-RES-JB
    11. 127
    Prev
    Next
    INDEX
    Explanations

    phrases related to discrimination or inequality

    oai_token-act-pair · gpt-3.5-turbo

    mentions or discussions of disparity

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

    No Comments

    Negative Logits
    ħĭ
    -0.99
    ¥µ
    -0.83
    doms
    -0.77
    ĨĴ
    -0.72
    æ©Ł
    -0.69
    OME
    -0.68
    urst
    -0.66
    ĻĤ
    -0.65
    å¸
    -0.65
    uge
    -0.64
    POSITIVE LOGITS
    allel
    1.18
    liament
    1.00
    anoia
    0.96
    imony
    0.91
    vati
    0.84
    ison
    0.80
    ity
    0.80
    amount
    0.76
    ion
    0.75
    cel
    0.75
    Activations Density 0.007%

    No Known Activations