INDEX

Explanations

references to the currency "dollar"

oai_token-act-pair · gpt-3.5-turbo

references to the dollar currency

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

ettings

-0.78

KEN

-0.71

 Aval

-0.71

ãĤ¤ãĥĪ

-0.69

CRIP

-0.66

inen

-0.66

 Flavoring

-0.65

Hav

-0.65

udic

-0.64

 Exper

-0.64

POSITIVE LOGITS

 dollar

1.00

dollar

0.90

hyde

0.90

peg

0.78

 dollars

0.77

ollar

0.77

($)

0.75

 Dollar

0.74

mented

0.73

 sterling

0.73

Activations Density 0.025%

references to the currency "dollar"

references to the dollar currency

No Comments

No Known Activations