INDEX

Explanations

phrases related to setting something aside or putting something off

oai_token-act-pair · gpt-3.5-turbo

instances of the phrase "put aside."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

oc

-0.66

wyn

-0.66

eway

-0.66

acker

-0.61

 coefficients

-0.61

cat

-0.60

rounder

-0.58

gio

-0.58

Ã¡s

-0.57

rio

-0.56

POSITIVE LOGITS

heid

1.04

 aside

1.01

bats

0.72

TextColor

0.70

manship

0.70

MENTS

0.69

comings

0.68

âĦ¢:

0.66

à©

0.63

mental

0.63

Activations Density 0.006%

phrases related to setting something aside or putting something off

instances of the phrase "put aside."

No Comments

No Known Activations