INDEX

Explanations

mentions of political figures and actions

oai_token-act-pair · gpt-3.5-turbo

references to political figures and events

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

Nusra

-0.83

[&

-0.71

Mesh

-0.70

ĪĴ

-0.70

 nuns

-0.70

lua

-0.68

 cafes

-0.67

Lua

-0.66

ackets

-0.66

 Canal

-0.66

POSITIVE LOGITS

 Donald

1.15

 President

1.15

Mr

1.14

 president

1.04

realDonaldTrump

1.03

 businessman

1.02

 dictator

1.02

 Defendant

1.02

 mogul

1.01

 billionaire

1.01

Activations Density 0.675%

mentions of political figures and actions

references to political figures and events

No Comments

No Known Activations