INDEX

Explanations

phrases related to personal and physical actions

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

 pama

-0.92

 guma

-0.86

<bos>

-0.84

 susun

-0.82

 ilang

-0.79

 katun

-0.77

 tanong

-0.76

 maging

-0.75

membrance

-0.74

 pinak

-0.74

POSITIVE LOGITS

 pregn

0.99

 reluct

0.98

 himself

0.98

himself

0.97

 disreg

0.96

 peppa

0.95

 michelin

0.93

 unden

0.92

 intermitt

0.91

 impra

0.89

Activations Density 0.687%

phrases related to personal and physical actions

No Comments

No Known Activations