© 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. 6645
    Prev
    Next
    INDEX
    Explanations

    phrases indicating an action or impact

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating actions or states of being

    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
     Columb
    -0.64
    rones
    -0.63
    eteenth
    -0.63
    igor
    -0.62
    comings
    -0.61
    Cub
    -0.60
    ston
    -0.59
    estern
    -0.58
    CLUD
    -0.58
    locked
    -0.57
    POSITIVE LOGITS
     create
    1.22
     educate
    1.16
     revise
    1.15
     remove
    1.14
     shorten
    1.12
     reduce
    1.12
     introduce
    1.11
     elevate
    1.10
     minimize
    1.10
     simplify
    1.10
    Activations Density 0.163%

    No Known Activations