© 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. 10-RES-JB
    11. 22124
    Prev
    Next
    INDEX
    Explanations

    phrases related to decision-making and conflicting interests

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to self-interest and decision-making motivations

    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
    drop
    -0.88
    ori
    -0.74
     Trace
    -0.73
    anmar
    -0.69
    wayne
    -0.69
    leted
    -0.66
    dra
    -0.66
    etheless
    -0.65
    Lens
    -0.63
    Saharan
    -0.63
    POSITIVE LOGITS
     interests
    1.76
    interest
    1.34
     convenience
    1.24
     safety
    1.19
     interest
    1.17
     sake
    1.14
     wellbeing
    1.13
     agendas
    1.11
     aesthetics
    1.10
     needs
    1.08
    Activations Density 0.621%

    No Known Activations