INDEX

Explanations

programming constructs related to function definitions and execution

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

^(@)

-0.98

 doubtnut

-0.94

Efq

-0.92

 Anſ

-0.88

 ་་

-0.87

 Jefus

-0.86

.³

-0.84

ſelves

-0.84

 purpoſe

-0.83

ſelf

-0.83

POSITIVE LOGITS

0.72

0.62

↵

0.61

|(

0.54

mid

0.50

||

0.48

|$

0.45

richTextPanel

0.44

↵↵↵

0.43

0.42

Activations Density 0.134%

programming constructs related to function definitions and execution

No Comments

No Known Activations