INDEX

Explanations

comment blocks in documentation or code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

]<<"

-0.61

BeginInit

-0.58

 spies

-0.54

 EClass

-0.54

EDEFAULT

-0.53

 gainera

-0.52

TargetException

-0.52

แห

-0.52

 оригіналу

-0.50

StandardCharsets

-0.50

POSITIVE LOGITS

Rüyada

0.66

Spoljašnje

0.64

SpringBootTest

0.60

AlterField

0.59

новниш

0.59

principalTable

0.59

Personendaten

0.59

mlung

0.57

 useStyles

0.56

ymmetric

0.56

Activations Density 0.031%

comment blocks in documentation or code

No Comments

No Known Activations