INDEX

Explanations

directional location terms, particularly focusing on the aspects of east and west

oai_token-act-pair · gpt-3.5-turbo

directional geographic descriptors

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

ioned

-0.74

 delinquent

-0.68

thood

-0.66

 guiActiveUn

-0.66

Score

-0.65

pload

-0.65

elist

-0.62

ello

-0.60

 expire

-0.60

 showc

-0.58

POSITIVE LOGITS

west

1.02

east

0.99

 Territories

0.94

wards

0.91

 Queensland

0.84

western

0.83

outheast

0.82

 latitude

0.82

lake

0.78

 corner

0.73

Activations Density 0.070%

directional location terms, particularly focusing on the aspects of east and west

directional geographic descriptors

No Comments

No Known Activations