INDEX

Explanations

names of people or entities in a news context

oai_token-act-pair · gpt-3.5-turbo

references to specific individuals or institutions involved in significant activities or decisions

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

 Definitions

-0.70

 clich

-0.70

 contrasts

-0.69

inguished

-0.67

 commons

-0.67

simple

-0.66

 contrast

-0.66

azeera

-0.66

basic

-0.64

inctions

-0.63

POSITIVE LOGITS

 secretly

1.15

 plans

0.98

 rumored

0.96

 leaked

0.92

 blackmail

0.91

 planned

0.89

 mull

0.87

 undisclosed

0.84

 imminent

0.84

 plotting

0.84

Activations Density 0.454%

names of people or entities in a news context

references to specific individuals or institutions involved in significant activities or decisions

No Comments

No Known Activations