INDEX

Explanations

phrases referring to methods or approaches

oai_token-act-pair · gpt-3.5-turbo

phrases that describe methods or approaches to doing something

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

ĸļ

-0.98

usters

-0.75

orescent

-0.71

uster

-0.71

oubted

-0.70

itor

-0.65

noxious

-0.65

ropolitan

-0.65

elaide

-0.64

eele

-0.63

POSITIVE LOGITS

fare

1.27

finding

1.11

ward

1.01

point

1.00

forward

0.97

 forward

0.94

points

0.92

station

0.90

finder

0.86

kell

0.85

Activations Density 0.049%

phrases referring to methods or approaches

phrases that describe methods or approaches to doing something

No Known Activations