INDEX

Explanations

words related to travel destinations

oai_token-act-pair · gpt-3.5-turbo

references to destinations

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

appa

-0.88

aps

-0.79

conn

-0.74

lee

-0.73

morph

-0.72

erd

-0.72

tymology

-0.72

IGHTS

-0.71

ooks

-0.71

 oxide

-0.70

POSITIVE LOGITS

 destination

1.09

 Destination

1.04

 destinations

0.99

 traveler

0.78

 location

0.72

 whence

0.72

 locale

0.68

 locations

0.64

 Mecca

0.64

 Cruise

0.64

Activations Density 0.021%

words related to travel destinations

references to destinations

No Comments

No Known Activations