© 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. 11-RES-JB
    11. 15744
    Prev
    Next
    INDEX
    Explanations

    phrases related to dining and alcohol consumption

    oai_token-act-pair · gpt-3.5-turbo

    references to emotional experiences and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oday
    -0.43
    anon
    -0.36
     Chiefs
    -0.33
     SHARES
    -0.32
     Presbyter
    -0.31
    rella
    -0.31
     vs
    -0.30
     but
    -0.30
     replaced
    -0.30
    arer
    -0.30
    POSITIVE LOGITS
    ä½ľ
    0.43
    ãĤ¹ãĥĪ
    0.42
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    0.41
    DAY
    0.41
    ãĤ¦ãĤ¹
    0.41
    NetMessage
    0.40
    ãĤ´ãĥ³
    0.40
    ¶
    0.40
     exha
    0.40
    ¥ŀ
    0.39
    Activations Density 2.375%

    No Known Activations