INDEX

Explanations

adjectives indicating strong beliefs or loyalty

oai_token-act-pair · gpt-3.5-turbo

words that indicate strong personal beliefs or unwavering support

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

ammy

-1.05

hops

-0.91

nesota

-0.83

ombies

-0.74

ammers

-0.72

uden

-0.72

NetMessage

-0.72

ovember

-0.70

APH

-0.70

anders

-0.68

POSITIVE LOGITS

ly

1.10

ness

0.85

wart

0.83

 supporter

0.76

 staunch

0.76

nesses

0.74

ELY

0.71

ity

0.70

 exponent

0.70

kowski

0.69

Activations Density 0.027%

adjectives indicating strong beliefs or loyalty

words that indicate strong personal beliefs or unwavering support

No Comments

No Known Activations