INDEX

Explanations

mentions of the word "war."

oai_token-act-pair · gpt-3.5-turbo

instances of the word "War" and related numerical values or indicators

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

essee

-0.92

ħĭ

-0.76

OGR

-0.67

 drawer

-0.64

Ħ¢

-0.64

 explan

-0.61

 wired

-0.61

 Seller

-0.61

 livest

-0.59

 topp

-0.59

POSITIVE LOGITS

rior

1.50

riors

1.46

fare

1.27

locks

1.22

lords

1.20

ped

1.17

ping

1.16

lord

1.15

lock

1.07

bler

1.02

Activations Density 0.038%

mentions of the word "war."

instances of the word "War" and related numerical values or indicators

No Comments

No Known Activations