© 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. 2728
    Prev
    Next
    INDEX
    Explanations

    phrases about maximizing or optimizing something

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing the desire to maximize outcomes or benefits

    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
    riad
    -0.80
    mare
    -0.80
    masters
    -0.71
    ¡
    -0.68
    ĪĴ
    -0.68
    ĸ
    -0.67
    wa
    -0.66
    dro
    -0.66
    shall
    -0.65
    gar
    -0.65
    POSITIVE LOGITS
     dstg
    0.87
    iary
    0.69
     capitalize
    0.67
     distingu
    0.65
     avoided
    0.64
     srfAttach
    0.63
    udos
    0.60
     posterior
    0.60
     achievable
    0.60
     dispel
    0.60
    Activations Density 0.030%

    No Known Activations