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. 10-RES-JB
    6. 17341
    Prev
    Next
    INDEX
    Explanations

    phrases related to political or ideological manipulation for personal gain

    oai_token-act-pair · gpt-3.5-turbo

    language related to exploitation for personal or political gain

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DragonMagazine
    -0.74
    tackle
    -0.72
    TPPStreamerBot
    -0.72
    çīĪ
    -0.68
    etooth
    -0.67
    reflect
    -0.66
     Trace
    -0.65
    ibr
    -0.65
     Bei
    -0.62
    CLOSE
    -0.61
    POSITIVE LOGITS
     profit
    1.26
     agendas
    1.12
     profits
    1.11
     Profit
    1.07
     gratification
    1.04
     blackmail
    1.02
     nefarious
    1.00
     agenda
    0.97
     predetermined
    0.95
     advantage
    0.94
    Activations Density 0.577%

    No Known Activations