© 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. 8-RES-JB
    11. 5107
    Prev
    Next
    INDEX
    Explanations

    phrases related to left-wing political ideologies

    oai_token-act-pair · gpt-3.5-turbo

    references to left-wing political ideologies or affiliations

    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
    ulhu
    -0.76
    »Ĵ
    -0.72
     Plum
    -0.71
     Pell
    -0.70
     Dickinson
    -0.63
    pload
    -0.61
     Prol
    -0.60
     Richards
    -0.60
    ãĤ©
    -0.60
     Chill
    -0.59
    POSITIVE LOGITS
    wing
    1.29
    hander
    1.26
    handed
    1.21
    leaning
    1.16
    sided
    1.10
    footed
    1.09
    facing
    1.04
    hand
    1.00
    biased
    0.99
    eyed
    0.98
    Activations Density 0.051%

    No Known Activations