INDEX

Explanations

phrases related to things being new

oai_token-act-pair · gpt-3.5-turbo

repeated phrases emphasizing "new" and "and" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

hoe

-0.83

ashtra

-0.81

utterstock

-0.79

ãĤ©

-0.75

SHIP

-0.74

é¾

-0.73

Timeout

-0.68

argon

-0.67

kov

-0.66

oler

-0.66

POSITIVE LOGITS

leans

0.88

 shiny

0.72

 sund

0.70

angled

0.68

exclusive

0.68

 exciting

0.68

 refreshed

0.67

worldly

0.67

iations

0.67

 debunked

0.65

Activations Density 0.138%

phrases related to things being new

repeated phrases emphasizing "new" and "and" in various contexts

No Comments

No Known Activations