© 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. 22326
    Prev
    Next
    INDEX
    Explanations

    verbs following a particular structure in which a subject is asked to perform an action

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "to" followed by verbs or actions

    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
    productive
    -0.69
     Kop
    -0.64
     Feld
    -0.62
    ////////////////////////////////
    -0.62
    ults
    -0.62
    quickShipAvailable
    -0.61
     Appears
    -0.60
    abiding
    -0.59
     genesis
    -0.58
    finding
    -0.58
    POSITIVE LOGITS
     intervene
    1.12
     participate
    1.11
     join
    1.11
     clarify
    1.09
     accompany
    1.07
     nominate
    1.07
     leave
    1.06
     submit
    1.04
     marry
    1.01
     give
    1.01
    Activations Density 0.107%

    No Known Activations