INDEX

Explanations

words related to physical places or geographical locations

oai_token-act-pair · gpt-3.5-turbo

mentions of "location."

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

vous

-0.98

jin

-0.89

unes

-0.82

missions

-0.79

ights

-0.78

squ

-0.77

ework

-0.76

haw

-0.76

tails

-0.75

qs

-0.74

POSITIVE LOGITS

 location

1.06

 locations

1.03

 landmarks

0.77

 locate

0.77

 Location

0.73

 geographically

0.72

URA

0.71

 locality

0.71

 relocation

0.69

 coordinates

0.68

Activations Density 0.028%

words related to physical places or geographical locations

mentions of "location."

No Comments

No Known Activations