INDEX

Explanations

numbers and mathematical operations

oai_token-act-pair · gpt-3.5-turbo

phrases indicating large quantities or numerical values

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

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

rius

-0.83

rog

-0.77

lar

-0.69

grim

-0.68

©¶æ

-0.68

lon

-0.66

 Zionism

-0.65

Prev

-0.65

venge

-0.65

xton

-0.64

POSITIVE LOGITS

 pages

0.90

 editions

0.88

 hours

0.85

 years

0.84

 degrees

0.81

 minutes

0.79

 acres

0.79

 IMAGES

0.78

 entries

0.78

 intersections

0.77

Activations Density 0.044%

numbers and mathematical operations

phrases indicating large quantities or numerical values

No Comments

No Known Activations