INDEX

Explanations

mentions of historical events related to war, specifically World War II

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

 sher

-0.71

OGR

-0.68

APS

-0.67

say

-0.65

doi

-0.65

QUI

-0.63

DEF

-0.62

 prosecut

-0.62

 predictive

-0.61

ITY

-0.60

POSITIVE LOGITS

II

1.36

Two

1.12

III

1.08

XII

0.95

 Three

0.92

ii

0.90

0.88

XVI

0.88

VII

0.86

planes

0.85

Activations Density 0.021%

mentions of historical events related to war, specifically World War II

No Comments

No Known Activations