INDEX

Explanations

the word "bystander" or related terms referring to individuals observing events

oai_token-act-pair · gpt-3.5-turbo

terms related to people who observe or witness events

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

amas

-0.70

omo

-0.68

arta

-0.68

ishop

-0.67

osis

-0.65

kamp

-0.64

icient

-0.63

esta

-0.63

anyahu

-0.62

omatic

-0.61

POSITIVE LOGITS

 bystand

1.40

 bystanders

1.21

 spectators

0.99

 onlook

0.97

 spectator

0.95

ĸļ

0.75

 thereto

0.75

 drown

0.73

rities

0.71

stration

0.71

Activations Density 0.007%

the word "bystander" or related terms referring to individuals observing events

terms related to people who observe or witness events

No Comments

No Known Activations