© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3217
    Prev
    Next
    INDEX
    Explanations

    phrases indicating willingness to take action

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "put" and its variations in a variety of contexts

    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
    externalActionCode
    -0.81
    yan
    -0.69
     Examiner
    -0.65
    uary
    -0.62
    alias
    -0.61
     Sample
    -0.60
    riott
    -0.59
    Legendary
    -0.59
     Associated
    -0.57
     unfocusedRange
    -0.57
    POSITIVE LOGITS
     forth
    1.05
    tin
    1.00
     together
    0.97
     aside
    0.96
    rid
    0.95
    tering
    0.88
    rescent
    0.84
    ongh
    0.83
    downs
    0.79
    tered
    0.77
    Activations Density 0.063%

    No Known Activations