© 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. 2-RES-JB
    11. 12057
    Prev
    Next
    INDEX
    Explanations

    phrases related to large natural formations or phenomena

    oai_token-act-pair · gpt-3.5-turbo

    references to icebergs and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dos
    -0.81
    eming
    -0.81
    eff
    -0.79
    parts
    -0.75
    verb
    -0.75
    akin
    -0.74
    alde
    -0.73
    GP
    -0.72
    expression
    -0.71
    phis
    -0.70
    POSITIVE LOGITS
     iceberg
    1.55
     glacier
    0.93
     volcano
    0.79
     snowball
    0.74
     waters
    0.74
     Glacier
    0.73
     parachute
    0.72
     lettuce
    0.71
     Titanic
    0.71
     Whale
    0.71
    Activations Density 0.014%

    No Known Activations