INDEX

Explanations

references to a time period before the current one

oai_token-act-pair · gpt-3.5-turbo

references to past events or time periods

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

"previous"

Explanation Uploaded by User

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

lees

-0.80

umes

-0.75

icles

-0.74

lee

-0.72

icle

-0.71

olor

-0.70

rosso

-0.69

mel

-0.69

acus

-0.68

blind

-0.67

POSITIVE LOGITS

decade

1.01

 incarnation

0.91

vernment

0.90

 occupant

0.88

 generation

0.88

 batch

0.86

 year

0.84

 millennium

0.83

 month

0.81

 week

0.80

Activations Density 0.061%

references to a time period before the current one

references to past events or time periods

"previous"

No Comments

No Known Activations