INDEX

Explanations

occurrences of variable definitions in the context of code snippets

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

RegistryLite

-0.66

ValueStyle

-0.57

Vidite

-0.56

StoryboardSegue

-0.56

Rüyada

-0.55

 صوتيه

-0.55

:✨

-0.54

:],

-0.54

rungsseite

-0.54

ENIE

-0.53

POSITIVE LOGITS

 purpoſe

0.84

 ſmall

0.73

 pleaſure

0.71

neſs

0.71

 reaſon

0.70

 ſen

0.68

 houſe

0.66

 myſelf

0.65

 greateſt

0.65

 uncin

0.64

Activations Density 0.240%

occurrences of variable definitions in the context of code snippets

No Comments

No Known Activations