INDEX

Explanations

Text information or descriptions related to various characters or profiles in different scenarios

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

MessageOf

-0.47

cademic

-0.46

 volup

-0.46

 CascadeType

-0.46

 Schuh

-0.45

ConstraintMaker

-0.45

withIdentifier

-0.45

ijuana

-0.45

TargetException

-0.44

 Jahrgang

-0.44

POSITIVE LOGITS

 text

1.39

 Text

1.28

text

1.25

 texts

1.21

Text

1.20

 TEXT

1.18

TEXT

1.18

 texted

1.03

 texte

1.02

Texts

1.01

Activations Density 0.067%

Text information or descriptions related to various characters or profiles in different scenarios

No Comments

No Known Activations