© 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. 13434
    Prev
    Next
    INDEX
    Explanations

    variations of the word "alternate" or "alternating"

    oai_token-act-pair · gpt-3.5-turbo

    terms related to alternation and the concept of shifting or varying patterns

    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
    Delivery
    -0.70
    HEAD
    -0.65
     Coffin
    -0.65
    mouth
    -0.63
     Soldiers
    -0.62
     Belief
    -0.62
     Hanson
    -0.61
     Famous
    -0.61
    HR
    -0.61
    Dri
    -0.61
    POSITIVE LOGITS
     altern
    1.24
    etheless
    1.00
     alternating
    0.96
    atile
    0.82
    atives
    0.81
    atility
    0.80
    icio
    0.79
     horizont
    0.78
    daq
    0.78
     newcom
    0.77
    Activations Density 0.008%

    No Known Activations