INDEX

Explanations

phrases related to a small quantity or degree of something

oai_token-act-pair · gpt-3.5-turbo

frequently used adverbs and filler words that convey a sense of quality or emphasis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

)].

-0.72

 Coil

-0.70

 Warlock

-0.67

 Divinity

-0.67

)=(

-0.67

 shitty

-0.65

 vibration

-0.65

 experimentation

-0.64

 sacrific

-0.64

 compliments

-0.64

POSITIVE LOGITS

azeera

0.89

ãĥķãĤ©

0.81

reet

0.71

ihadi

0.70

hatt

0.69

ãĥ©ãĥ³

0.69

abet

0.69

abouts

0.69

ãĥĳ

0.68

ould

0.67

Activations Density 1.155%

phrases related to a small quantity or degree of something

frequently used adverbs and filler words that convey a sense of quality or emphasis

No Comments

No Known Activations