INDEX

Explanations

mentions of specific mountain ranges

oai_token-act-pair · gpt-3.5-turbo

references to mountains

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

tle

-0.87

lich

-0.72

NER

-0.70

cer

-0.66

cci

-0.66

Cam

-0.65

PAR

-0.65

OUT

-0.64

Â·Â·

-0.63

Labor

-0.63

POSITIVE LOGITS

 mountains

1.06

 Mountains

0.98

 biome

0.81

dale

0.81

 footh

0.79

 challeng

0.79

lake

0.79

 valley

0.78

 valleys

0.78

terday

0.78

Activations Density 0.012%

mentions of specific mountain ranges

references to mountains

No Comments

No Known Activations