© 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. 3-RES-JB
    11. 11497
    Prev
    Next
    INDEX
    Explanations

    words related to sharp criticism or cleverly pointed remarks

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "acting" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĸļ
    -0.97
    éĹĺ
    -0.85
     Dare
    -0.83
     Katz
    -0.81
    OPLE
    -0.79
     Sins
    -0.78
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.74
     Territories
    -0.72
     Cors
    -0.71
     Stur
    -0.71
    POSITIVE LOGITS
    robat
    1.19
    oust
    1.06
    uity
    1.05
    ricular
    1.00
    rylic
    0.99
    rament
    0.98
    orns
    0.97
    acia
    0.97
    rop
    0.96
    ros
    0.93
    Activations Density 0.006%

    No Known Activations