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

    Neuronpedia

    Jacobian LensNEW
    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. 9-RES-JB
    11. 18243
    Prev
    Next
    INDEX
    Explanations

    terms related to functionality or transformation and the role or function of a person or object within a system

    oai_token-act-pair · gpt-3.5-turbo

    verbs that indicate an action or role played by a subject

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    doms
    -0.85
    ancies
    -0.83
    zees
    -0.77
    iev
    -0.76
    errors
    -0.76
    lees
    -0.76
    akis
    -0.74
    rants
    -0.73
    intent
    -0.73
    projects
    -0.72
    POSITIVE LOGITS
     conduit
    1.22
     intermediary
    1.18
     catalyst
    1.18
     liaison
    1.16
     reminder
    1.14
     guide
    1.11
     surrogate
    1.06
     gateway
    1.04
     placeholder
    1.03
     primer
    1.01
    Activations Density 0.227%

    No Known Activations