INDEX

Explanations

phrases and terms related to intentions and objectives

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

principalTable

-0.93

 विश्वसनीयता

-0.91

 MainAxisSize

-0.85

PhysRev

-0.83

 ligiloj

-0.80

 चीज़ों

-0.77

EndContext

-0.76

OGND

-0.76

 متعلقه

-0.74

Aspiration

-0.74

POSITIVE LOGITS

 allowed

0.59

 think

0.55

 aimed

0.53

 allow

0.49

aim

0.49

us

0.47

put

0.46

体

0.46

 made

0.45

<bos>

0.45

Activations Density 0.139%

phrases and terms related to intentions and objectives

No Comments

No Known Activations