INDEX

Explanations

words related to excitement or things that evoke excitement

oai_token-act-pair · gpt-3.5-turbo

words related to excitement or thrilling experiences

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

enegger

-0.84

externalActionCode

-0.80

 Dragonbound

-0.76

SHIP

-0.71

heit

-0.68

beard

-0.68

strap

-0.67

breaker

-0.66

ÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂł

-0.66

 Millennium

-0.65

POSITIVE LOGITS

ursions

1.33

ursion

1.31

usable

1.22

ision

1.10

retion

1.09

uses

1.06

used

1.06

itement

1.04

ission

1.03

ipient

1.02

Activations Density 0.009%

words related to excitement or things that evoke excitement

words related to excitement or thrilling experiences

No Comments

No Known Activations