INDEX

Explanations

phrases related to positions and roles within organizations

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

 levis

-0.84

 effe

-0.80

 meis

-0.76

 abnorm

-0.75

ohr

-0.74

 erec

-0.73

 zimmer

-0.72

 handels

-0.71

 kombi

-0.71

mef

-0.70

POSITIVE LOGITS

VP

0.55

 Operations

0.53

дравству

0.51

 operations

0.49

 Parsing

0.48

ಛ

0.47

 adjoint

0.47

 overseeing

0.46

 Customization

0.45

vp

0.43

Activations Density 0.098%

phrases related to positions and roles within organizations

No Comments

No Known Activations