INDEX

Explanations

names of political figures, especially those associated with a specific political campaign

oai_token-act-pair · gpt-3.5-turbo

names of political figures and their associated activities

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

 ratification

-0.70

 Mortal

-0.69

 debtor

-0.69

VID

-0.65

 Jagu

-0.62

umar

-0.60

require

-0.60

 Icar

-0.58

Ü

-0.58

 licence

-0.58

POSITIVE LOGITS

andowski

0.99

 Spicer

0.98

 Conway

0.88

 aide

0.85

 aides

0.83

verage

0.83

osta

0.81

ashington

0.79

 Priebus

0.79

hler

0.78

Activations Density 0.030%

names of political figures, especially those associated with a specific political campaign

names of political figures and their associated activities

No Comments

No Known Activations