INDEX

Explanations

differences in societal perceptions and norms between different groups

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

 Baillargeon

-0.58

OGND

-0.54

 bezeichneter

-0.50

InjectAttribute

-0.48

liday

-0.48

 الرياضيه

-0.47

 typelib

-0.45

 Shakspeare

-0.44

rency

-0.42

hematics

-0.41

POSITIVE LOGITS

 chrysler

0.66

 isuzu

0.65

 chevrolet

0.63

Tja

0.62

 lamborghini

0.62

 levering

0.61

 stihl

0.61

 hilux

0.61

FTFY

0.60

 nimmer

0.59

Activations Density 0.189%

differences in societal perceptions and norms between different groups

No Comments

No Known Activations