INDEX

Explanations

the word "that"

oai_token-act-pair · gpt-3.5-turbo

definitive statements or assertions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

GC

-0.72

Rated

-0.70

AAA

-0.70

Variable

-0.69

ATES

-0.69

——

-0.68

ED

-0.67

ADE

-0.67

Hyper

-0.65

 engages

-0.64

POSITIVE LOGITS

agher

0.73

 reve

0.67

roma

0.65

 pupp

0.65

erb

0.64

wagen

0.64

rome

0.64

hound

0.63

dylib

0.63

gnu

0.63

Activations Density 0.000%

the word "that"

definitive statements or assertions

No Comments

No Known Activations