INDEX

Explanations

the word "one" in a variety of contexts

oai_token-act-pair · gpt-3.5-turbo

phrases that express quantities or references to multiple items or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

ensen

-0.66

etermination

-0.65

âĢ

-0.60

body

-0.57

ins

-0.56

 aside

-0.55

quez

-0.54

 streng

-0.54

lees

-0.54

anse

-0.54

POSITIVE LOGITS

 these

0.89

these

0.82

my

0.76

our

0.74

those

0.73

 those

0.72

them

0.69

 ours

0.65

ses

0.63

thouse

0.63

Activations Density 0.086%

the word "one" in a variety of contexts

phrases that express quantities or references to multiple items or events

No Comments

No Known Activations