INDEX

Explanations

words related to patriotism and patriotic sentiments

oai_token-act-pair · gpt-3.5-turbo

references to patriotism and national pride

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

Medium

-0.77

-0.75

RH

-0.74

upon

-0.73

orne

-0.73

Solution

-0.73

changes

-0.72

fell

-0.71

Jenn

-0.68

Ward

-0.67

POSITIVE LOGITS

 patriotic

1.28

 patri

1.12

 patriotism

1.06

 patriot

0.97

 duty

0.95

 commemor

0.87

 anthem

0.83

ilitary

0.81

dinand

0.77

 citiz

0.77

Activations Density 0.013%

words related to patriotism and patriotic sentiments

references to patriotism and national pride

No Comments

No Known Activations