INDEX

Explanations

words related to safety and security

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

 apprehen

-0.93

 increa

-0.80

fta

-0.78

 intersper

-0.78

 reluct

-0.76

 impra

-0.75

 disagre

-0.74

 quitted

-0.73

fuf

-0.73

fte

-0.69

POSITIVE LOGITS

 safe

1.28

 Safe

1.24

safe

1.22

Safe

1.21

 SAFE

1.12

SAFE

1.10

unsafe

0.98

 safer

0.96

saf

0.94

saf

0.91

Activations Density 0.065%

words related to safety and security

No Comments

No Known Activations