INDEX

Explanations

phrases related to positions and states of being in certain situations, often emphasizing advantage or disadvantage

oai_token-act-pair · gpt-3.5-turbo

prepositions indicating position or location

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

leys

-0.73

ZA

-0.71

 mysql

-0.67

entity

-0.64

Disclaimer

-0.62

 methodology

-0.62

leck

-0.62

 DATA

-0.61

 relates

-0.60

 evid

-0.59

POSITIVE LOGITS

 peril

0.84

 jeopardy

0.80

unin

0.76

aterasu

0.75

hon

0.74

 unwelcome

0.74

 unch

0.73

chuk

0.73

 trouble

0.71

 happiest

0.69

Activations Density 0.207%

phrases related to positions and states of being in certain situations, often emphasizing advantage or disadvantage

prepositions indicating position or location

No Comments

No Known Activations