INDEX

Explanations

syntax and structure elements within code snippets or programming languages

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

TA

-0.49

 fare

-0.45

 coba

-0.44

 walk

-0.43

 Super

-0.42

 tunnel

-0.41

walk

-0.41

Mack

-0.41

inburgh

-0.41

llings

-0.41

POSITIVE LOGITS

findpost

1.00

 تضيفلها

0.88

mybatisplus

0.85

 jadx

0.84

 '\\;'

0.78

StreetMap

0.75

@[+][

0.74

 forKey

0.72

تقاوى

0.72

AddTagHelper

0.71

Activations Density 0.614%

syntax and structure elements within code snippets or programming languages

No Comments

No Known Activations