INDEX

Explanations

words related to academia or academic institutions

oai_token-act-pair · gpt-3.5-turbo

mentions of academic professionals and institutions

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Islands

-0.70

 Territories

-0.66

 Niagara

-0.64

val

-0.64

 Vikings

-0.62

ggles

-0.61

Gun

-0.59

 Species

-0.58

 Island

-0.58

LIST

-0.58

POSITIVE LOGITS

 academics

0.98

hran

0.95

 lecturer

0.92

essors

0.90

 academia

0.88

essor

0.88

chool

0.87

ertation

0.87

olor

0.85

 academ

0.84

Activations Density 0.017%

words related to academia or academic institutions

mentions of academic professionals and institutions

No Comments

No Known Activations