INDEX

Explanations

words related to medical conditions and terms related to specific locations

oai_token-act-pair · gpt-3.5-turbo

words related to 'bul'

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

heid

-0.79

esan

-0.76

LEASE

-0.74

hew

-0.73

 CLSID

-0.69

afort

-0.67

 Estate

-0.65

EEE

-0.65

ointed

-0.65

 Defender

-0.64

POSITIVE LOGITS

wark

1.18

bul

1.01

acies

0.97

leted

0.93

iatus

0.89

orescent

0.87

untary

0.86

ols

0.85

¸

0.85

acan

0.82

Activations Density 0.034%

words related to medical conditions and terms related to specific locations

words related to 'bul'

No Comments

No Known Activations