© 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. 688
    Prev
    Next
    INDEX
    Explanations

    phrases related to motivations or driving forces behind actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate motivation or influence

    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
    olit
    -0.89
    ilet
    -0.89
    iatrics
    -0.85
     transitioned
    -0.83
    spect
    -0.83
    ibi
    -0.82
    inis
    -0.82
    pei
    -0.79
    ciation
    -0.79
    gregation
    -0.78
    POSITIVE LOGITS
     curiosity
    0.87
     fears
    0.86
     ideology
    0.83
     passions
    0.82
     promises
    0.82
     visions
    0.82
     fear
    0.81
     impulses
    0.81
     factors
    0.80
     bribes
    0.79
    Activations Density 0.119%

    No Known Activations