INDEX

Explanations

phrases indicating an amount of time spent in a specific location

oai_token-act-pair · gpt-3.5-turbo

instances of the word "for" followed by numerical references to durations

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

Introduced

-0.67

illin

-0.66

Ohio

-0.65

urred

-0.65

uckland

-0.64

KK

-0.63

fleet

-0.63

aults

-0.62

=>

-0.61

Â´

-0.61

POSITIVE LOGITS

 awhile

1.12

 instance

1.08

 example

1.03

geries

1.00

bidden

0.99

gotten

0.93

aging

0.88

 starters

0.88

 months

0.86

 purposes

0.84

Activations Density 0.197%

phrases indicating an amount of time spent in a specific location

instances of the word "for" followed by numerical references to durations

No Comments

No Known Activations