INDEX

Explanations

words or phrases describing a location or a place

oai_token-act-pair · gpt-3.5-turbo

phrases indicating a continual state or characteristic

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

soon

-0.82

ģ«

-0.68

regate

-0.67

yet

-0.67

illions

-0.66

ellar

-0.65

now

-0.65

))))

-0.64

ptoms

-0.64

actually

-0.63

POSITIVE LOGITS

 regarded

0.91

 fascinated

0.88

 shrouded

0.79

 wary

0.78

 skeptical

0.74

 elusive

0.73

 considered

0.72

 admired

0.72

 uneasy

0.72

 reluctant

0.71

Activations Density 0.144%

words or phrases describing a location or a place

phrases indicating a continual state or characteristic

No Comments

No Known Activations