© 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. 3-RES-JB
    11. 10687
    Prev
    Next
    INDEX
    Explanations

    mentions of different ideologies

    oai_token-act-pair · gpt-3.5-turbo

    references to various ideologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    de
    -0.75
    upon
    -0.73
     Mamm
    -0.72
    ells
    -0.72
    ten
    -0.71
    EVA
    -0.70
    shall
    -0.69
    upper
    -0.67
    hap
    -0.67
    teen
    -0.67
    POSITIVE LOGITS
     ideology
    1.09
     indoctr
    0.96
    eering
    0.92
     theorist
    0.89
     guiActiveUn
    0.89
     ideologies
    0.83
     affiliation
    0.83
     underpin
    0.81
    ologue
    0.80
    ologies
    0.80
    Activations Density 0.014%

    No Known Activations