INDEX

Explanations

words related to strong emotional reactions or conflicts

oai_token-act-pair · gpt-3.5-turbo

words related to life sciences or vividness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

soDeliveryDate

-0.72

 cannons

-0.71

conservancy

-0.68

 cannon

-0.64

yout

-0.64

senal

-0.64

slot

-0.62

piece

-0.62

queue

-0.60

 livest

-0.60

POSITIVE LOGITS

ivid

1.00

uation

0.81

lies

0.78

itives

0.77

 Hots

0.75

escent

0.73

itri

0.71

ition

0.69

acion

0.69

inosaur

0.69

Activations Density 0.036%

words related to strong emotional reactions or conflicts

words related to life sciences or vividness

No Comments

No Known Activations