INDEX

Explanations

phrases related to locations or specific sites

oai_token-act-pair · gpt-3.5-turbo

phrases indicating locations or sites of events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

Enlarge

-0.73

Ĥİ

-0.70

hirt

-0.70

iev

-0.67

\\\\\\\\

-0.67

 mell

-0.65

 Marketable

-0.65

 inbox

-0.64

cn

-0.64

 patience

-0.63

POSITIVE LOGITS

 Apostle

0.73

 nearest

0.71

 contamination

0.69

 refuge

0.68

 Sanctuary

0.66

 infringing

0.64

site

0.64

 landmarks

0.63

 entrances

0.63

 historic

0.63

Activations Density 0.142%

phrases related to locations or specific sites

phrases indicating locations or sites of events

No Comments

No Known Activations