INDEX

Explanations

specific named entities like business names, locations, and titles

oai_token-act-pair · gpt-3.5-turbo

prominent names and phrases related to institutions or services

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 tremend

-0.72

çĶ°

-0.72

 deficit

-0.72

 streng

-0.71

 carbohyd

-0.69

 sacrific

-0.68

 steroids

-0.66

 bowel

-0.65

 predec

-0.64

 punishing

-0.64

POSITIVE LOGITS

âĦ¢

0.91

ibrary

0.82

Girl

0.82

Jr

0.81

0.79

Knight

0.79

()

0.78

wordpress

0.77

 Profile

0.77

List

0.76

Activations Density 0.209%

specific named entities like business names, locations, and titles

prominent names and phrases related to institutions or services

No Comments

No Known Activations