INDEX

Explanations

numerical values related to quantities or measurements

oai_token-act-pair · gpt-3.5-turbo

numerical data and statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

landers

-0.78

STR

-0.77

stocks

-0.76

flies

-0.74

hands

-0.73

hook

-0.73

haven

-0.73

anders

-0.72

 Hawaiian

-0.71

 LOOK

-0.70

POSITIVE LOGITS

per

1.51

per

1.11

 teasp

0.97

Per

0.95

Per

0.92

pci

0.90

pc

0.90

pc

0.88

PER

0.86

 cents

0.83

Activations Density 0.089%

numerical values related to quantities or measurements

numerical data and statistics

No Comments

No Known Activations