INDEX

Explanations

time-related expressions, particularly those indicating years and time passed

oai_token-act-pair · gpt-3.5-turbo

phrases related to the passage of time

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

ãĥ¤

-0.76

SourceFile

-0.76

Redd

-0.73

anooga

-0.72

Talk

-0.66

Bey

-0.65

edo

-0.65

topic

-0.64

icum

-0.64

Cho

-0.63

POSITIVE LOGITS

 hindsight

0.93

 imprison

0.74

 incarcer

0.73

 spent

0.69

 captivity

0.68

 counting

0.68

 adulthood

0.67

 retrospect

0.67

 matured

0.67

Ã©t

0.65

Activations Density 0.153%

time-related expressions, particularly those indicating years and time passed

phrases related to the passage of time

No Comments

No Known Activations