INDEX

Explanations

phrases related to changes or fluctuations in quantities

oai_token-act-pair · gpt-3.5-turbo

phrases indicating increases in numerical values or metrics

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

çīĪ

-0.75

Planet

-0.71

æ³

-0.69

edin

-0.69

thing

-0.66

ctr

-0.65

iquette

-0.64

trap

-0.63

wcsstore

-0.63

soever

-0.61

POSITIVE LOGITS

efficiency

1.06

effic

0.91

 incidence

0.88

 popularity

0.86

 revenues

0.84

ordinate

0.84

 revenue

0.79

 intensity

0.78

 circulation

0.77

 concentration

0.77

Activations Density 0.086%

phrases related to changes or fluctuations in quantities

phrases indicating increases in numerical values or metrics

No Comments

No Known Activations