© 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. 16364
    Prev
    Next
    INDEX
    Explanations

    phrases related to unity or coming together

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "united" and its variations

    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
    ©¶æ
    -0.90
     Roof
    -0.78
     Fiction
    -0.73
     Advertisement
    -0.66
    aches
    -0.66
     Nou
    -0.64
     Journalists
    -0.63
     Peer
    -0.62
     Gamble
    -0.62
     Fargo
    -0.62
    POSITIVE LOGITS
     united
    1.10
     unite
    0.97
    mble
    0.80
    iband
    0.80
    éĹĺ
    0.78
    ãĤ¤ãĥĪ
    0.76
     unity
    0.76
    ĸļ
    0.76
    idas
    0.74
     unified
    0.73
    Activations Density 0.010%

    No Known Activations