© 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. 10-RES-JB
    11. 6678
    Prev
    Next
    INDEX
    Explanations

    words related to various persons or entities with the name "Gra"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "Gra" in various contexts

    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
     CPC
    -0.71
    ional
    -0.68
    nikov
    -0.68
     intervals
    -0.63
    gdala
    -0.62
     Clapper
    -0.60
     Dragonbound
    -0.59
     Clarkson
    -0.58
     Corpus
    -0.57
    payer
    -0.57
    POSITIVE LOGITS
    ffiti
    1.72
    veyard
    1.42
    veland
    1.34
    ppa
    1.27
    eme
    1.26
    fx
    1.24
    vel
    1.19
    ffe
    1.18
    fters
    1.17
    ven
    1.16
    Activations Density 0.030%

    No Known Activations