INDEX

Explanations

mentions of academic institutions

oai_token-act-pair · gpt-3.5-turbo

references to academic institutions or the concept of academia

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

ter

-0.77

baugh

-0.71

PIN

-0.70

tz

-0.68

theless

-0.65

tering

-0.64

ding

-0.64

fm

-0.64

lessness

-0.64

walking

-0.64

POSITIVE LOGITS

emia

1.08

emies

1.06

 Acad

0.95

olesc

0.90

uria

0.89

essor

0.88

ilib

0.87

alon

0.84

acia

0.84

illary

0.84

Activations Density 0.008%

mentions of academic institutions

references to academic institutions or the concept of academia

No Comments

No Known Activations