INDEX

Explanations

phrases related to political figures and events

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

to

-0.79

-0.77

 through

-0.77

-0.75

has

-0.75

top

-0.75

for

-0.74

by

-0.74

as

-0.74

 with

-0.73

POSITIVE LOGITS

 effe

2.50

fta

2.48

ftu

2.48

aen

2.47

 nece

2.37

mef

2.37

 thut

2.36

fup

2.32

 seiz

2.32

fto

2.30

Activations Density 0.046%

phrases related to political figures and events

No Comments

No Known Activations