INDEX

Explanations

phrases emphasizing a particular point or aspect, especially with conditions or scenarios attached

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Opere

-0.60

]}

-0.59

 esattamente

-0.57

Voci

-0.56

 Ressource

-0.56

:+:

-0.55

 Paglinawan

-0.55

física

-0.53

-0.52

 sullo

-0.52

POSITIVE LOGITS

 apprehen

1.30

 gaily

1.26

 unspeak

1.25

 shenan

1.23

 intersper

1.17

 rascal

1.15

 gratify

1.13

 quitted

1.12

 vainly

1.11

 pymysql

1.10

Activations Density 0.094%

phrases emphasizing a particular point or aspect, especially with conditions or scenarios attached

No Comments

No Known Activations