INDEX

Explanations

references to the context and framework of discussions or analyses

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

 ſta

-0.91

 houſe

-0.80

 pleaſure

-0.79

 purpoſe

-0.78

 myſelf

-0.74

 ſeveral

-0.73

 ſever

-0.73

 Majefty

-0.72

 ſtate

-0.72

 Diſ

-0.72

POSITIVE LOGITS

PreferredItem

0.83

posedge

0.60

OfSize

0.60

CJK

0.59

olge

0.59

ItemBackground

0.58

 ThemeData

0.57

Abitanti

0.57

 بهد

0.57

ieteur

0.56

Activations Density 0.445%

references to the context and framework of discussions or analyses

No Comments

No Known Activations