INDEX

Explanations

phrases related to making decisions or coming to realizations

oai_token-act-pair · gpt-3.5-turbo

instances of decision-making and realizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

idium

-0.78

heed

-0.66

arettes

-0.66

 Mali

-0.65

arta

-0.62

Guest

-0.62

TY

-0.61

enta

-0.60

Appearance

-0.58

aka

-0.58

POSITIVE LOGITS

yss

0.84

culus

0.76

 instinctively

0.76

undai

0.72

 sugg

0.70

uyomi

0.70

yrinth

0.66

 unnecess

0.65

ãĤ¦ãĤ¹

0.64

 wondering

0.62

Activations Density 0.255%

phrases related to making decisions or coming to realizations

instances of decision-making and realizations

No Comments

No Known Activations