Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 17191
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal and political entities like states, nations, and legislation

    oai_token-act-pair · gpt-3.5-turbo

    repeated phrases or conjunctions that help to emphasize connections between ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DragonMagazine
    -0.84
    etr
    -0.71
    Adapt
    -0.70
    >[
    -0.67
    agnetic
    -0.67
    physical
    -0.66
    FT
    -0.66
    elo
    -0.66
    luck
    -0.65
    ¯
    -0.64
    POSITIVE LOGITS
     elsewhere
    1.61
     abroad
    1.52
     neighbouring
    1.21
     neighboring
    1.18
     internationally
    1.14
     mainland
    1.14
     southeastern
    1.12
     northwestern
    1.11
     southwestern
    1.11
     Midwest
    1.11
    Activations Density 0.146%

    No Known Activations