INDEX

Explanations

mentions of specific locations or events, particularly related to memorials and days of remembrance

oai_token-act-pair · gpt-3.5-turbo

references to memorials and commemorative events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

avage

-0.81

lings

-0.74

arent

-0.68

inion

-0.68

ucket

-0.67

aves

-0.67

nesses

-0.67

liness

-0.66

eva

-0.65

ahn

-0.64

POSITIVE LOGITS

izing

0.95

izers

0.92

ization

0.92

 plaque

0.90

 memorial

0.90

brance

0.90

 remembrance

0.89

izes

0.89

abilia

0.86

 Sloan

0.85

Activations Density 0.020%

mentions of specific locations or events, particularly related to memorials and days of remembrance

references to memorials and commemorative events

No Comments

No Known Activations