© 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. 9-RES-JB
    11. 1708
    Prev
    Next
    INDEX
    Explanations

    instances or situations of comparison and contrast

    oai_token-act-pair · gpt-3.5-turbo

    instances of frequency qualifiers indicating how often something occurs

    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
    BuyableInstoreAndOnline
    -0.84
    heed
    -0.66
    pointer
    -0.65
    onite
    -0.64
     Uriel
    -0.63
     Schwar
    -0.62
    lash
    -0.57
    ctor
    -0.55
    abe
    -0.55
    rift
    -0.54
    POSITIVE LOGITS
     respects
    1.53
     cases
    1.47
     ways
    1.20
     instances
    1.20
     contexts
    1.15
     embodiments
    1.14
     regards
    1.13
     circumstances
    1.11
     situations
    1.07
     places
    1.07
    Activations Density 0.070%

    No Known Activations