INDEX

Explanations

phrases related to decision-making and analysis

oai_token-act-pair · gpt-3.5-turbo

phrases related to various aspects of decision-making and conditions surrounding choices

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

 sidx

-0.64

 helicop

-0.60

 nutshell

-0.60

liest

-0.57

aho

-0.57

uben

-0.54

iann

-0.51

 bunny

-0.51

icer

-0.50

xton

-0.50

POSITIVE LOGITS

 Flavoring

0.71

Reviewer

0.63

aft

0.62

itars

0.62

akens

0.61

 Dish

0.57

CLR

0.56

 Rouhani

0.56

Redd

0.56

âĢ¢âĢ¢

0.55

Activations Density 1.146%

phrases related to decision-making and analysis

phrases related to various aspects of decision-making and conditions surrounding choices

No Comments

No Known Activations