© 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. 7-RES-JB
    11. 21498
    Prev
    Next
    INDEX
    Explanations

    the name "Bob" with a higher activation for the full name "Billy Bob."

    oai_token-act-pair · gpt-3.5-turbo

    names and terms related to specific individuals and entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ngth
    -0.91
    eele
    -0.76
    ources
    -0.73
    forth
    -0.67
     pockets
    -0.62
     CFR
    -0.61
     territ
    -0.60
    ample
    -0.59
     vantage
    -0.59
     retract
    -0.58
    POSITIVE LOGITS
    Cola
    0.81
    ĵĺ
    0.79
    Ń·
    0.74
    ר
    0.74
     ACTIONS
    0.71
    ãĥŁ
    0.69
     Mahjong
    0.65
    Ïī
    0.65
    ãĤ´ãĥ³
    0.65
     Archdemon
    0.63
    Activations Density 0.481%

    No Known Activations