© 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. 8-RES-JB
    6. 22682
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to news or articles

    oai_token-act-pair · gpt-3.5-turbo

    references to media sources, particularly images and their attributions

    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
    sic
    -0.66
    <|endoftext|>
    -0.61
     reper
    -0.59
    CONCLUS
    -0.57
    ItemTracker
    -0.56
    anwhile
    -0.55
     challeng
    -0.54
    pled
    -0.53
     nostalg
    -0.53
     territ
    -0.53
    POSITIVE LOGITS
     Shutterstock
    0.78
    utterstock
    0.76
    Phys
    0.72
     âĢº
    0.68
     Caption
    0.67
    )--
    0.62
    Madison
    0.59
    Associated
    0.57
     Sask
    0.57
     Cohn
    0.57
    Activations Density 0.305%

    No Known Activations