INDEX

Explanations

references to smoking-related content

oai_token-act-pair · gpt-3.5-turbo

instances of the word "smoking."

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

 Defenders

-0.72

Nou

-0.71

tell

-0.71

assian

-0.70

 Corinthians

-0.68

HCR

-0.67

translation

-0.65

SER

-0.64

Philipp

-0.64

SEC

-0.63

POSITIVE LOGITS

 smoking

1.25

 cessation

1.24

 smoked

1.07

 smoker

1.06

 cigarettes

1.05

 cigars

1.03

 smoke

1.00

 tobacco

0.96

 smokes

0.93

uana

0.90

Activations Density 0.010%

references to smoking-related content

instances of the word "smoking."

No Comments

No Known Activations