INDEX

Explanations

references to tax-related terms

oai_token-act-pair · gpt-3.5-turbo

terms related to taxation

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ENE

-0.74

sbm

-0.70

ilst

-0.68

lihood

-0.68

Ò

-0.67

 Flavoring

-0.67

 Ment

-0.67

hots

-0.66

Sensor

-0.66

uggest

-0.66

POSITIVE LOGITS

 liabilities

0.90

 evasion

0.90

 payable

0.85

 levied

0.85

 havens

0.85

 dodging

0.85

 liability

0.85

 taxes

0.83

 dodge

0.82

 taxation

0.78

Activations Density 0.038%

references to tax-related terms

terms related to taxation

No Comments

No Known Activations