© 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. 0-RES-JB
    11. 22681
    Prev
    Next
    INDEX
    Explanations

    multi-word phrases with the word "staggered"

    oai_token-act-pair · gpt-3.5-turbo

    terms related to scheduling and organizational structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adow
    -0.84
    abal
    -0.81
    ftime
    -0.80
    atos
    -0.79
    hops
    -0.77
     Miko
    -0.76
    natureconservancy
    -0.72
    boro
    -0.71
     endif
    -0.71
    uture
    -0.69
    POSITIVE LOGITS
     Remastered
    1.59
    DIS
    0.99
     staggered
    0.71
    reys
    0.63
     Duchess
    0.63
    aniel
    0.62
     SEM
    0.62
    EMBER
    0.61
    ASS
    0.60
    NESS
    0.60
    Activations Density 0.001%

    No Known Activations