INDEX

Explanations

references to puzzles and problem-solving activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

antMatchers

-0.73

RegressionTest

-0.67

cheiden

-0.65

 resourceCulture

-0.64

NegativeButton

-0.62

ropriate

-0.55

AccessorTable

-0.54

 levis

-0.53

atguigu

-0.53

Становништво

-0.53

POSITIVE LOGITS

 puzzle

2.02

 puzzles

1.86

 mystery

1.78

 mysteries

1.62

 Puzzle

1.61

puzzle

1.60

 riddle

1.59

Puzzle

1.51

 Puzzles

1.50

mystery

1.49

Activations Density 0.229%

references to puzzles and problem-solving activities

No Comments

No Known Activations