INDEX

Explanations

code-related instructions and patterns related to configuration or definitions in programming

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

 виправивши

-0.61

 shutil

-0.58

 TextAlign

-0.57

ims

-0.55

 redor

-0.54

BagLayout

-0.53

okovic

-0.49

 Kran

-0.49

kungen

-0.49

opel

-0.47

POSITIVE LOGITS



0.75

CodeAttribute

0.66

ruby

0.64

 referenties

0.61

//=

0.59

års

0.59

Materiál

0.58

ॅ

0.58

 Caval

0.57

 Ruby

0.57

Activations Density 0.177%

code-related instructions and patterns related to configuration or definitions in programming

No Comments

No Known Activations