INDEX

Explanations

words related to being impacted or affected by something

oai_token-act-pair · gpt-3.5-turbo

terms related to being affected or impacted by situations or events

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

cipled

-0.67

 aspiration

-0.64

outh

-0.62

pires

-0.62

YC

-0.62

çĦ

-0.60

ope

-0.60

cia

-0.60

CHA

-0.58

alt

-0.58

POSITIVE LOGITS

by

1.19

 adversely

1.11

 negatively

1.01

BY

0.92

by

0.90

By

0.87

 financially

0.84

 acutely

0.81

 disproportionately

0.81

By

0.80

Activations Density 0.051%

words related to being impacted or affected by something

terms related to being affected or impacted by situations or events

No Comments

No Known Activations