INDEX

Explanations

language related to patriotism and the Patriot Act

oai_token-act-pair · gpt-3.5-turbo

words associated with patriotism and related concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

orne

-0.70

er

-0.69

Tool

-0.68

worm

-0.68

caster

-0.68

err

-0.67

 accelerator

-0.67

bench

-0.65

ussed

-0.65

way

-0.64

POSITIVE LOGITS

riots

0.92

 patriotic

0.89

 patri

0.85

 patriot

0.85

 Patriot

0.84

éĹĺ

0.78

riot

0.76

sburg

0.75

dinand

0.75

 patriotism

0.74

Activations Density 0.032%

language related to patriotism and the Patriot Act

words associated with patriotism and related concepts

No Comments

No Known Activations