INDEX

Explanations

terms related to medical conditions, specifically those ending in 'oph'

oai_token-act-pair · gpt-3.5-turbo

terminology related to medical conditions, specifically those involving the eyes and vision

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

forth

-0.77

 Gemini

-0.71

nels

-0.70

LOAD

-0.68

FIN

-0.66

 Clarks

-0.66

 Crescent

-0.65

Sox

-0.64

WARD

-0.63

 Grizzlies

-0.63

POSITIVE LOGITS

osph

1.28

osate

1.27

ouse

1.18

oph

1.15

omore

1.04

agic

1.04

ilia

1.04

ouses

1.04

ysics

1.03

agy

1.01

Activations Density 0.012%

terms related to medical conditions, specifically those ending in 'oph'

terminology related to medical conditions, specifically those involving the eyes and vision

No Comments

No Known Activations