INDEX

Explanations

phrases related to intensity or extreme situations

oai_token-act-pair · gpt-3.5-turbo

references to various states of being or conditions

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

 Bene

-0.52

pired

-0.49

owler

-0.49

 Dani

-0.48

encers

-0.48

 Photograph

-0.47

 dstg

-0.46

Built

-0.46

icators

-0.46

rix

-0.46

POSITIVE LOGITS

livion

0.64

 conclud

0.61

 obscurity

0.54

dos

0.54

 limb

0.52

 defences

0.51

 wilderness

0.51

 difficulties

0.50

 productive

0.50

 defenses

0.50

Activations Density 1.455%

phrases related to intensity or extreme situations

references to various states of being or conditions

No Comments

No Known Activations