INDEX

Explanations

proper nouns, specifically related to titles or names

oai_token-act-pair · gpt-3.5-turbo

keywords related to specific titles or names, particularly in media and gaming contexts

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

Negative Logits

lier

-0.80

aneously

-0.78

activity

-0.75

 forestry

-0.74

istically

-0.72

 exception

-0.72

ren

-0.69

ously

-0.69

 fisherman

-0.67

pton

-0.66

POSITIVE LOGITS

hift

1.18

peed

1.15

aurus

1.08

mith

1.08

Ago

1.08

hops

1.04

pread

1.03

pace

1.02

ystem

0.99

 Parties

0.98

Activations Density 0.172%

proper nouns, specifically related to titles or names

keywords related to specific titles or names, particularly in media and gaming contexts

No Known Activations