INDEX

Explanations

technical language and formulas, particularly in a scientific or mathematical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<eos>

-0.93

↵↵

-0.78

%)

-0.71

JTextField

-0.68

%)

-0.67

“

-0.66

-0.65

er

-0.64

↵↵↵↵↵

-0.64

POSITIVE LOGITS

 purpoſe

0.93

 numberWith

0.93

 itſelf

0.93

mockMvc

0.90

 StringTokenizer

0.89

 Majefty

0.87

 doubtnut

0.87

 ReSharper

0.85

躇

0.85

 greateſt

0.84

Activations Density 1.498%

technical language and formulas, particularly in a scientific or mathematical context

No Comments

No Known Activations