INDEX

Explanations

phrases related to financial deductions or deductions in general

oai_token-act-pair · gpt-3.5-turbo

references to tax deductions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

hell

-0.78

 Nieto

-0.77

cock

-0.70

 Rebell

-0.70

Ã±a

-0.70

wave

-0.67

anco

-0.66

NK

-0.63

builders

-0.63

Factory

-0.62

POSITIVE LOGITS

 deducted

0.87

 deductions

0.87

 allowable

0.87

edu

0.85

roit

0.84

aneous

0.81

 deductible

0.79

 allowance

0.78

payer

0.77

 deduct

0.77

Activations Density 0.034%

phrases related to financial deductions or deductions in general

references to tax deductions

No Comments

No Known Activations