INDEX

Explanations

phrases related to historical events, particularly World War II

oai_token-act-pair · gpt-3.5-turbo

mentions of World War II

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

OGR

-0.77

ITY

-0.71

QUI

-0.67

ITIES

-0.66

 sher

-0.62

*/(

-0.62

 slee

-0.61

obook

-0.61

 prosecut

-0.59

panic

-0.59

POSITIVE LOGITS

II

1.27

III

1.10

Two

1.06

 Three

0.92

0.91

ii

0.87

VII

0.87

XII

0.85

0.84

Activations Density 0.021%

phrases related to historical events, particularly World War II

mentions of World War II

No Comments

No Known Activations