INDEX

Explanations

words related to a specific political figure (Harper) in various contexts

oai_token-act-pair · gpt-3.5-turbo

mentions of the politician Stephen Harper

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

mble

-0.94

âĵĺ

-0.83

sembly

-0.80

ECTION

-0.80

etermination

-0.78

olean

-0.78

ership

-0.77

ural

-0.77

ersion

-0.77

uality

-0.75

POSITIVE LOGITS

Collins

1.08

 Harper

0.95

weather

0.80

 Trudeau

0.79

hawks

0.68

DOM

0.68

shire

0.67

pin

0.66

 Conservatives

0.64

 Goose

0.63

Activations Density 0.006%

words related to a specific political figure (Harper) in various contexts

mentions of the politician Stephen Harper

No Comments

No Known Activations