INDEX

Explanations

words related to being worried or troubled about something

oai_token-act-pair · gpt-3.5-turbo

expressions of concern

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

iller

-0.78

arb

-0.75

aro

-0.72

avour

-0.69

alter

-0.67

avorite

-0.66

OVA

-0.64

oba

-0.62

ingers

-0.62

heres

-0.61

POSITIVE LOGITS

 about

1.32

 ABOUT

1.12

about

1.08

 lest

0.97

 About

0.93

ingly

0.92

lessly

0.82

About

0.81

 enough

0.80

 regarding

0.79

Activations Density 0.053%

words related to being worried or troubled about something

expressions of concern

No Comments

No Known Activations