INDEX

Explanations

terms related to financial crimes, such as money laundering

oai_token-act-pair · gpt-3.5-turbo

occurrences of the letter "R" in the text

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

-0.74

 Guinness

-0.70

grass

-0.70

 Dolphin

-0.69

 Totem

-0.68

CPR

-0.68

enegger

-0.66

ãĥ¼ãĥĨãĤ£

-0.66

Pom

-0.65

 Granger

-0.64

POSITIVE LOGITS

senal

1.25

ansom

1.17

outing

1.15

outine

1.14

acing

1.12

ICH

1.12

ework

1.09

ascal

1.08

acco

1.08

anc

1.07

Activations Density 0.032%

terms related to financial crimes, such as money laundering

occurrences of the letter "R" in the text

No Comments

No Known Activations