INDEX

Explanations

the word "war" in various contexts

oai_token-act-pair · gpt-3.5-turbo

occurrences of the term "war."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

sembly

-0.82

essee

-0.81

ĸļ

-0.77

htaking

-0.76

aminer

-0.74

İĭ

-0.73

afort

-0.69

Ħ¢

-0.69

 tremend

-0.69

 vulnerable

-0.67

POSITIVE LOGITS

rior

1.41

riors

1.36

fare

1.35

war

1.04

ring

1.01

lords

0.89

ney

0.87

fighter

0.87

hammer

0.84

bucks

0.84

Activations Density 0.006%

the word "war" in various contexts

occurrences of the term "war."

No Comments

No Known Activations