© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3-RES-JB
    11. 21108
    Prev
    Next
    INDEX
    Explanations

    words related to a specific concept or metaphor, particularly the concept of a crossroads

    oai_token-act-pair · gpt-3.5-turbo

    multiple instances of the word "cross," indicating a focus on intersections or significant points of convergence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    姫
    -0.73
    nant
    -0.71
    ERSON
    -0.65
    andum
    -0.64
    cffff
    -0.64
    ICAN
    -0.64
    lain
    -0.64
    acious
    -0.63
     PLAN
    -0.62
     Peb
    -0.62
    POSITIVE LOGITS
    roads
    1.28
    bow
    1.07
    cross
    0.97
    bows
    0.92
    cutting
    0.88
    bones
    0.87
    hair
    0.85
    bench
    0.83
    road
    0.83
    wal
    0.79
    Activations Density 0.014%

    No Known Activations