© 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. 23414
    Prev
    Next
    INDEX
    Explanations

    information about people or entities being well-known for specific attributes or actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating recognition or reputation of individuals

    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
     voluntary
    -0.74
    tein
    -0.71
     Nam
    -0.66
    plet
    -0.64
     Sierra
    -0.63
     Bots
    -0.61
    secution
    -0.61
     Yugoslavia
    -0.60
    otom
    -0.58
     RSA
    -0.57
    POSITIVE LOGITS
    л
    0.96
    Ô
    0.89
    ãĥĦ
    0.85
    Offline
    0.84
    ÙĨ
    0.80
    ãĥĥãĥĪ
    0.76
    ãĤ¼ãĤ¦ãĤ¹
    0.75
    س
    0.75
    bryce
    0.70
    @@@@@@@@
    0.69
    Activations Density 0.053%

    No Known Activations