INDEX

Explanations

dates related to certain events or occurrences

oai_token-act-pair · gpt-3.5-turbo

references to specific time periods, particularly the word "late" followed by a number

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

ourge

-0.85

inguished

-0.81

apego

-0.81

hyde

-0.80

IUM

-0.74

edIn

-0.71

quished

-0.68

abilia

-0.67

onite

-0.66

 Lives

-0.66

POSITIVE LOGITS

 afternoon

0.98

imester

0.87

 mornings

0.79

 infancy

0.76

 manner

0.75

 increments

0.75

 morning

0.74

 evening

0.74

0.73

Activations Density 0.040%

dates related to certain events or occurrences

references to specific time periods, particularly the word "late" followed by a number

No Comments

No Known Activations