© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 4077
    Prev
    Next
    INDEX
    Explanations

    phrases related to "pods"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "pod" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    illard
    -0.98
     ATI
    -0.91
    inventoryQuantity
    -0.81
    çĶ°
    -0.78
    inelli
    -0.72
     AVG
    -0.72
    iard
    -0.71
     Cullen
    -0.69
     ç¥ŀ
    -0.68
    ItemImage
    -0.67
    POSITIVE LOGITS
     Pod
    3.91
     pod
    3.67
    pod
    3.36
    Pod
    3.17
     pods
    2.70
     podcasts
    1.28
     Podcast
    1.26
     Pablo
    1.20
     podcast
    1.20
    podcast
    1.19
    Activations Density 0.019%

    No Known Activations