© 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. 10694
    Prev
    Next
    INDEX
    Explanations

    verbs that indicate making a conscious decision

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "choose" indicating decisions or choices being made

    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
    brance
    -0.78
    urst
    -0.70
    uum
    -0.69
    utenberg
    -0.67
    otor
    -0.66
    atomic
    -0.64
    ijk
    -0.64
    Net
    -0.63
    awar
    -0.61
    iter
    -0.61
    POSITIVE LOGITS
     chooses
    0.89
     chose
    0.89
     choose
    0.83
    axe
    0.81
     chosen
    0.78
     choices
    0.76
     ACTIONS
    0.76
     choosing
    0.71
     wisely
    0.70
    çĶŁ
    0.70
    Activations Density 0.026%

    No Known Activations