INDEX

Explanations

terms related to detailed explanations or elaborate descriptions

oai_token-act-pair · gpt-3.5-turbo

terms related to detailed explanations and descriptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 payday

-0.70

 adoption

-0.67

DOWN

-0.64

é¾įå¥ĳå£«

-0.63

 felon

-0.63

 runaway

-0.62

 enroll

-0.60

 Sector

-0.59

Ws

-0.59

 Tracker

-0.59

POSITIVE LOGITS

acies

1.31

istically

1.28

itating

1.23

istics

1.19

ately

1.13

itated

1.13

izing

1.09

itate

1.07

itative

1.05

atory

1.04

Activations Density 0.064%

terms related to detailed explanations or elaborate descriptions

terms related to detailed explanations and descriptions

No Comments

No Known Activations