INDEX

Explanations

TV shows, movie characters, journalists, and various alcohol beverages

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

 '\\;'

-0.79

MessageTagHelper

-0.72

<bos>

-0.72

السكان

-0.65

Географиясе

-0.63

вік

-0.62

WarningLevel

-0.62

SaveChangesAsync

-0.61

 Walkover

-0.60

 Administrativna

-0.59

POSITIVE LOGITS

 encomp

1.65

 impra

1.54

 indestru

1.53

 unve

1.48

 intersper

1.47

 unspeak

1.45

 hairc

1.36

 reluct

1.36

 depic

1.35

 disagre

1.35

Activations Density 0.248%

TV shows, movie characters, journalists, and various alcohol beverages

No Comments

No Known Activations