INDEX

Explanations

company and technology-related terms and acronyms

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Configuration

jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.6.hook_resid_post_16384_anthropic_fast_lr

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

torch.float32

Hook Point

blocks.6.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

HuggingFaceFW/fineweb

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-1.82

ⓧ

-0.72

 intersper

-0.56

 quitted

-0.53

 rejoin

-0.52

harmed

-0.52

 reconno

-0.51

 magnify

-0.51

Schön

-0.51

flä

-0.51

POSITIVE LOGITS

Sta

1.15

ST

1.11

Sta

1.00

Stu

0.96

st

0.94

sta

0.92

ST

0.92

 Moderato

0.87

 Hauteur

0.87

 Staf

0.86

Activations Density 0.381%

company and technology-related terms and acronyms

No Comments

No Known Activations