INDEX

Explanations

phrases related to academic lectures

oai_token-act-pair · gpt-3.5-turbo

mentions of lectures

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

Chain

-0.85

 eligibility

-0.69

ARA

-0.65

Ĥª

-0.64

enders

-0.64

vernight

-0.63

ansas

-0.63

 Border

-0.62

ãģ®éŃĶ

-0.62

luck

-0.62

POSITIVE LOGITS

 Lect

3.48

 lecture

3.20

 lectures

3.17

 lect

2.59

 lecturer

2.01

 sermon

1.83

 seminar

1.62

 seminars

1.59

 keynote

1.52

TED

1.42

Activations Density 0.024%

phrases related to academic lectures

mentions of lectures

No Known Activations