© 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. 11-RES-JB
    11. 18710
    Prev
    Next
    INDEX
    Explanations

    phrases containing proper names followed by verbs or actions

    oai_token-act-pair · gpt-3.5-turbo

    references to sources or credits in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rient
    -0.70
    terday
    -0.60
    ynchron
    -0.60
    neum
    -0.59
    theless
    -0.59
    soon
    -0.58
    ima
    -0.58
     fame
    -0.57
    estern
    -0.57
    rency
    -0.56
    POSITIVE LOGITS
    :
    0.85
     Provided
    0.83
     Cards
    0.75
    Card
    0.71
     CARD
    0.69
     Card
    0.68
     Sources
    0.65
    giving
    0.64
    :'
    0.63
     Wass
    0.63
    Activations Density 0.020%

    No Known Activations