INDEX

Explanations

mentions of teachers

oai_token-act-pair · gpt-3.5-turbo

references to teachers

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

tera

-0.70

rils

-0.66

ocene

-0.64

ankind

-0.61

 sclerosis

-0.61

00200000

-0.60

ril

-0.60

erenn

-0.59

sts

-0.59

croft

-0.58

POSITIVE LOGITS

 Teachers

1.01

 Teacher

0.99

 teacher

0.94

essor

0.92

heet

0.90

 teachers

0.89

girls

0.88

student

0.84

 educators

0.83

idget

0.81

Activations Density 0.018%

mentions of teachers

references to teachers

No Comments

No Known Activations