INDEX

Explanations

phrases related to tax deductions

oai_token-act-pair · gpt-3.5-turbo

terms related 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 @ 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

 Nieto

-0.87

cock

-0.75

Ã±a

-0.68

 constitu

-0.68

NK

-0.68

Hunt

-0.64

hell

-0.64

 Rebell

-0.64

 Iter

-0.63

anco

-0.63

POSITIVE LOGITS

 deductions

1.00

 allowance

0.99

 allowances

0.93

payer

0.91

 deductible

0.91

 deduction

0.90

 allowable

0.90

edu

0.86

 deducted

0.85

 deduct

0.84

Activations Density 0.025%

phrases related to tax deductions

terms related to tax deductions

No Comments

No Known Activations