INDEX

Explanations

instances where someone has been in a specific location

oai_token-act-pair · gpt-3.5-turbo

instances of the phrase "I was in" followed by a location or situation

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

Availability

-0.66

 larg

-0.65

Includes

-0.64

 newcomers

-0.60

($

-0.60

Jose

-0.60

 currents

-0.60

âĤ¬

-0.59

Residents

-0.59

 strings

-0.59

POSITIVE LOGITS

animate

0.80

ordinate

0.80

uggle

0.76

strument

0.74

pport

0.73

active

0.71

 unch

0.71

comed

0.70

utters

0.69

operative

0.69

Activations Density 0.222%

instances where someone has been in a specific location

instances of the phrase "I was in" followed by a location or situation

No Comments

No Known Activations