INDEX

Explanations

mentions of interest rates

oai_token-act-pair · gpt-3.5-turbo

references to interest rates

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

Interstitial

-0.85

 WATCHED

-0.84

ITNESS

-0.83

istar

-0.82

inem

-0.81

irgin

-0.79

iak

-0.79

 Flavoring

-0.77

essler

-0.76

nen

-0.75

POSITIVE LOGITS

payers

1.13

payer

1.07

 payable

1.00

 adjustment

0.86

uation

0.82

 rate

0.81

 payments

0.81

 rates

0.80

 fluctuations

0.78

 swaps

0.77

Activations Density 0.028%

mentions of interest rates

references to interest rates

No Comments

No Known Activations