INDEX

Explanations

phrases related to processes, particularly those involving setup and initialization in technical contexts

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

-0.75

 دیکھیے

-0.52

DoubleQuotes

-0.47

 HasFactory

-0.45

agram

-0.44

ритори

-0.44

 المح

-0.43

찰

-0.43

Му

-0.42

IInter

-0.42

POSITIVE LOGITS

 initial

0.98

initial

0.94

 INITIAL

0.90

 Initial

0.87

Initial

0.85

 inicial

0.81

 iniziale

0.80

 Inicial

0.80

INITIAL

0.79

 initialState

0.77

Activations Density 0.559%

phrases related to processes, particularly those involving setup and initialization in technical contexts

No Comments

No Known Activations