INDEX

Explanations

references to user-defined entities and variables in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/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.6.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

ⓧ

-0.84

 bezeichneter

-0.83

 useRouter

-0.77

GraphicsUnit

-0.75

 endblock

-0.74

setVerticalGroup

-0.72

tvguidetime

-0.72

MoveNext

-0.71

NewGuid

-0.70

 ActivatedRoute

-0.70

POSITIVE LOGITS

0.63

 groupBox

0.61

0.57

0.56

0.55

ไง

0.54

わずか

0.52

 skjø

0.52

שְׁ

0.51

 步骤

0.51

Activations Density 1.161%

references to user-defined entities and variables in code

No Comments

No Known Activations