INDEX

Explanations

phrases or terms related to time

oai_token-act-pair · gpt-3.5-turbo

word endings or morphemes that suggest specific grammatical constructions or references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

enegger

-0.89

riott

-0.61

 ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³

-0.60

ãĥ¤

-0.60

 Blaz

-0.58

 Benz

-0.58

 Robot

-0.57

 Austral

-0.57

door

-0.57

 antioxid

-0.56

POSITIVE LOGITS

nesota

1.09

amps

0.87

iae

0.83

ota

0.81

orum

0.76

OTA

0.75

kees

0.73

ATURE

0.72

ippi

0.71

oes

0.70

Activations Density 0.068%

phrases or terms related to time

word endings or morphemes that suggest specific grammatical constructions or references

No Comments

No Known Activations