INDEX

Explanations

specific locations or geographic references

oai_token-act-pair · gpt-3.5-turbo

phrases that refer to specific locations

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

vous

-0.97

jin

-0.91

missions

-0.84

tails

-0.80

ework

-0.78

unes

-0.77

squ

-0.77

qs

-0.76

tail

-0.74

haw

-0.73

POSITIVE LOGITS

 location

1.01

 locations

1.00

 landmarks

0.80

URA

0.78

 locality

0.75

 locate

0.73

 Location

0.70

 Brands

0.69

 vicinity

0.69

 coordinates

0.69

Activations Density 0.042%

specific locations or geographic references

phrases that refer to specific locations

No Comments

No Known Activations