INDEX

Explanations

phrases related to the word "switch."

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

za

-0.71

raq

-0.66

-0.60

 Upton

-0.59

ORED

-0.59

zza

-0.59

etermined

-0.59

issance

-0.59

lov

-0.58

illery

-0.58

POSITIVE LOGITS

blade

1.12

grass

1.01

gear

0.95

backs

0.94

 gears

0.86

 switch

0.82

switch

0.81

 between

0.80

 switches

0.80

over

0.77

Activations Density 0.030%

phrases related to the word "switch."

No Comments

No Known Activations