INDEX

Explanations

phrases asking about the meaning or implications of a given situation or concept

oai_token-act-pair · gpt-3.5-turbo

references to the terms "this" and "that" in relation to questioning meaning or significance

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

Not in Any Lists

No Comments

Negative Logits

mens

-1.00

mop

-0.91

culosis

-0.81

geons

-0.81

iencies

-0.81

ahime

-0.80

vic

-0.80

dos

-0.79

vard

-0.78

anas

-0.78

POSITIVE LOGITS

 entails

1.03

 mean

0.96

 meant

0.92

 entail

0.90

 means

0.88

 Means

0.82

 implies

0.82

 imply

0.78

 newfound

0.78

 boils

0.77

Activations Density 0.064%

phrases asking about the meaning or implications of a given situation or concept

references to the terms "this" and "that" in relation to questioning meaning or significance

No Comments

No Known Activations