INDEX

Explanations

instances of phrases related to a specific concept or argument present in the text

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

Certific

-0.53

Mó

-0.48

oncesto

-0.47

fetchall

-0.47

Vegeu

-0.46

AllowUser

-0.46

EFAULT

-0.45

Comun

-0.44

Rujuakan

-0.44

Nuestra

-0.44

POSITIVE LOGITS

 indestru

1.26

 shenan

1.19

 caprice

1.14

 reluct

1.14

 milf

1.10

 excru

1.08

 intersper

1.08

 unce

1.08

 perfet

1.07

 unden

1.07

Activations Density 0.145%

instances of phrases related to a specific concept or argument present in the text

No Comments

No Known Activations