INDEX

Explanations

phrases related to spatial orientation and medical terms within documents

oai_token-act-pair · gpt-3.5-turbo

terms related to axes in a scientific or mathematical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

esters

-1.00

rov

-0.90

odor

-0.79

atten

-0.76

frey

-0.74

esson

-0.73

namese

-0.72

anan

-0.72

doms

-0.70

ORE

-0.70

POSITIVE LOGITS

 axis

1.08

 mund

0.98

axis

0.88

illary

0.87

 axes

0.86

 stabil

0.85

 crank

0.82

 perpendicular

0.81

 jerk

0.79

 alignment

0.78

Activations Density 0.023%

phrases related to spatial orientation and medical terms within documents

terms related to axes in a scientific or mathematical context

No Comments

No Known Activations