INDEX

Explanations

specific phrases related to events, awards, scholarships, and programs

oai_token-act-pair · gpt-3.5-turbo

proper nouns associated with awards, surveys, and events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 queen

-0.81

 havens

-0.78

 unions

-0.76

 trouble

-0.71

 hiber

-0.70

 angles

-0.69

 parks

-0.67

 sources

-0.67

theless

-0.67

 communists

-0.67

POSITIVE LOGITS

âĦ¢

1.21

 Facility

1.19

 Series

1.15

 Fund

1.11

 Collection

1.11

 Initiative

1.10

 Authority

1.09

 Program

1.09

 Project

1.09

 Consortium

1.09

Activations Density 0.281%

specific phrases related to events, awards, scholarships, and programs

proper nouns associated with awards, surveys, and events

No Comments

No Known Activations