© 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. 1-RES-JB
    11. 20151
    Prev
    Next
    INDEX
    Explanations

    words related to travel and transportation

    oai_token-act-pair · gpt-3.5-turbo

    the presence of content that indicates completeness or fullness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FactoryReloaded
    -0.81
    DragonMagazine
    -0.74
     GOODMAN
    -0.66
    osate
    -0.65
    going
    -0.64
    ods
    -0.64
    raft
    -0.63
    earable
    -0.61
    enegger
    -0.61
     nitrogen
    -0.61
    POSITIVE LOGITS
    acs
    0.65
    eter
    0.64
     Rebell
    0.63
     Osh
    0.62
    eddy
    0.60
     Krist
    0.60
    lete
    0.59
    ãĥı
    0.58
    jong
    0.58
     Rooms
    0.58
    Activations Density 0.000%

    No Known Activations