© 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. 1067
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of "year"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of years

    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
     Hilbert
    -0.83
     Ic
    -0.77
     Shack
    -0.73
     Ou
    -0.71
     Labyrinth
    -0.68
    berman
    -0.67
     Bloom
    -0.67
     Hole
    -0.65
     Pebble
    -0.65
     Hubble
    -0.64
    POSITIVE LOGITS
    rha
    1.18
    izont
    0.91
    rr
    0.90
    interstitial
    0.89
    yr
    0.89
    rh
    0.86
    azines
    0.81
    thur
    0.81
    andom
    0.81
    umph
    0.79
    Activations Density 0.008%

    No Known Activations