INDEX

Explanations

phrases indicating a method or approach to do something

oai_token-act-pair · gpt-3.5-turbo

phrases indicating methods or approaches

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

avorite

-0.82

aples

-0.71

oppable

-0.70

usters

-0.68

uster

-0.65

noxious

-0.61

ĸļ

-0.61

irie

-0.60

ancies

-0.60

eneg

-0.58

POSITIVE LOGITS

fare

1.17

ward

1.08

 forward

1.03

forward

1.03

point

1.00

finding

0.93

to

0.91

points

0.89

station

0.89

finder

0.86

Activations Density 0.038%

phrases indicating a method or approach to do something

phrases indicating methods or approaches

No Comments

No Known Activations