© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 8977
    Prev
    Next
    INDEX
    Explanations

    phrases related to lists and collections

    oai_token-act-pair · gpt-3.5-turbo

    references to lists or enumerations of items or names

    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
    arent
    -0.71
    riott
    -0.64
    strike
    -0.62
     braking
    -0.62
    alam
    -0.62
     Technician
    -0.61
     cents
    -0.61
    ivals
    -0.61
    cause
    -0.60
    peria
    -0.60
    POSITIVE LOGITS
     littered
    1.29
     consisting
    1.23
     containing
    1.22
     contains
    1.20
     curated
    1.18
     comprised
    1.15
     overflowing
    1.12
     stocked
    1.11
     populated
    1.10
     lists
    1.10
    Activations Density 0.856%

    No Known Activations