INDEX

Explanations

YouTube video markers and descriptions

oai_token-act-pair · gpt-3.5-turbo

mentions of video content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 prose

-0.65

ospons

-0.65

lesi

-0.63

ertation

-0.62

wine

-0.62

pled

-0.60

nec

-0.60

lein

-0.60

ogi

-0.60

toc

-0.60

POSITIVE LOGITS

 flanked

0.74

 dilig

0.72

 ASIC

0.68

terday

0.67

chu

0.67

KT

0.66

agher

0.66

 Ãľ

0.66

ï¸ı

0.66

]'

0.64

Activations Density 0.073%

YouTube video markers and descriptions

mentions of video content

No Comments

No Known Activations