INDEX

Explanations

the word "ips."

oai_token-act-pair · gpt-3.5-turbo

references to "ips" or related suffixes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

 Aval

-0.70

WAYS

-0.68

 damned

-0.68

scape

-0.67

mates

-0.65

WAY

-0.65

 Saud

-0.65

 Defin

-0.63

 volumes

-0.62

\\\\\\\\\\\\\\\\

-0.62

POSITIVE LOGITS

etsk

1.04

ips

1.03

ilateral

1.03

aret

1.02

awed

1.01

ilon

0.99

olitan

0.98

hift

0.98

ilver

0.97

creen

0.96

Activations Density 0.010%

the word "ips."

references to "ips" or related suffixes

No Comments

No Known Activations