INDEX

Explanations

phrases related to evaluations and assessments

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Configuration

jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

standard

Context Size

1,024

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-0.77

DockStyle

-0.68

RunAsync

-0.61

WAUKEE

-0.58

 تانيه

-0.54

ivamente

-0.52

 Савезне

-0.51

 لينك

-0.51

 resultMap

-0.50

adecimal

-0.50

POSITIVE LOGITS

 intermitt

1.01

 unlaw

0.92

 bourgeo

0.91

 indestru

0.90

 simplif

0.89

 endom

0.89

 unden

0.88

 augus

0.87

 bordeaux

0.87

 cabrio

0.86

Activations Density 0.270%

phrases related to evaluations and assessments

No Comments

No Known Activations