Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 1114
    Prev
    Next
    INDEX
    Explanations

    phrases describing socio-economic struggles

    oai_token-act-pair · gpt-3.5-turbo

    issues related to socioeconomic challenges and inequalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ange
    -0.66
    CAP
    -0.65
    inth
    -0.64
    ocket
    -0.63
    Marsh
    -0.63
    west
    -0.62
    thur
    -0.61
    las
    -0.61
     Statue
    -0.60
    monster
    -0.60
    POSITIVE LOGITS
     themselves
    1.46
    selves
    1.16
     careers
    1.04
     voluntarily
    1.01
     their
    1.00
     selves
    0.99
     willingly
    0.97
     lifestyles
    0.90
     subsistence
    0.89
     socially
    0.89
    Activations Density 1.029%

    No Known Activations