INDEX

Explanations

phrases related to the banking industry and financial institutions

oai_token-act-pair · gpt-3.5-turbo

references to banks and lending institutions

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

 Horton

-0.68

 Loving

-0.62

Args

-0.62

++++++++++++++++

-0.62

 Fren

-0.62

imens

-0.62

 VIDE

-0.62

 Gaul

-0.61

ROR

-0.61

FLAG

-0.61

POSITIVE LOGITS

 banks

1.05

banks

1.02

creen

0.93

 banking

0.92

ystem

0.88

hops

0.86

 bankers

0.85

 bank

0.83

rupt

0.82

aturated

0.82

Activations Density 0.015%

phrases related to the banking industry and financial institutions

references to banks and lending institutions

No Comments

No Known Activations