© 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. 24052
    Prev
    Next
    INDEX
    Explanations

    mentions or references to the term "Blue"

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Blue" related to teams or entities

    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
    IFA
    -0.96
    Ö¼
    -0.86
    ROR
    -0.85
    _-
    -0.81
    NRS
    -0.80
    ãĤ¼ãĤ¦ãĤ¹
    -0.79
    UME
    -0.79
    ICH
    -0.79
    ETF
    -0.79
    SPONSORED
    -0.77
    POSITIVE LOGITS
    grass
    1.25
    berry
    1.20
     Blue
    1.10
    berries
    1.02
    prints
    1.01
    bird
    0.97
    blue
    0.93
    heart
    0.92
    hawk
    0.85
    ucer
    0.85
    Activations Density 0.010%

    No Known Activations