INDEX

Explanations

mentions of educational degrees

oai_token-act-pair · gpt-3.5-turbo

terms related to various types of academic degrees and qualifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

prop

-0.67

theless

-0.66

effect

-0.66

 Ambro

-0.64

 forcefully

-0.63

 Samson

-0.63

forth

-0.62

 urge

-0.61

 Crom

-0.60

 react

-0.59

POSITIVE LOGITS

ploma

1.45

 dissertation

1.04

 Degree

0.97

 tuition

0.95

 diploma

0.94

uates

0.93

 qualification

0.93

ertation

0.87

 Bachelor

0.86

 graduate

0.85

Activations Density 0.082%

mentions of educational degrees

terms related to various types of academic degrees and qualifications

No Comments

No Known Activations