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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 7-RES-JB
    6. 6298
    Prev
    Next
    INDEX
    Explanations

    words related to ideologies or political affiliations, particularly ending in 'ist' or 'ists'

    oai_token-act-pair · gpt-3.5-turbo

    words related to various "-ist" titles or ideologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    shown
    -0.73
    MENTS
    -0.72
    stall
    -0.69
    ãģ®éŃĶ
    -0.67
    ths
    -0.67
    ãĥ¼ãĥ«
    -0.67
    thening
    -0.66
    FACE
    -0.66
    STON
    -0.64
    cellent
    -0.64
    POSITIVE LOGITS
    otle
    0.86
    ribution
    0.83
    ricting
    0.81
    ische
    0.80
    orical
    0.78
     tendencies
    0.77
    geist
    0.76
    ribute
    0.76
    ophe
    0.74
    ischer
    0.73
    Activations Density 0.055%

    No Known Activations