INDEX

Explanations

information related to drug classification and regulation

oai_token-act-pair · gpt-3.5-turbo

references to drugs and their legal classifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 drum

-0.76

 reminis

-0.72

raham

-0.71

Mom

-0.69

 Conan

-0.68

 bartender

-0.67

 Cros

-0.67

sax

-0.67

 passionately

-0.66

ram

-0.65

POSITIVE LOGITS

 classification

1.31

 designation

1.31

 Classification

1.18

afety

1.18

 ineligible

1.14

 category

1.13

 blacklist

1.10

category

1.09

 disqualified

1.04

 classify

1.03

Activations Density 0.410%

information related to drug classification and regulation

references to drugs and their legal classifications

No Comments

No Known Activations