INDEX

Explanations

descriptions and mentions of hearing or listening

oai_token-act-pair · gpt-3.5-turbo

references to hearing or knowledge acquisition

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 Leilan

-0.69

ardless

-0.67

raviolet

-0.67

iant

-0.64

 Hebdo

-0.64

ãĥł

-0.64

rha

-0.63

thumbnails

-0.60

isites

-0.60

anship

-0.60

POSITIVE LOGITS

 roar

1.16

 voices

1.09

 loud

1.07

 voice

1.07

 scream

1.06

 whine

1.05

 moan

1.04

 whispers

1.03

 noises

1.02

 screams

1.01

Activations Density 0.112%

descriptions and mentions of hearing or listening

references to hearing or knowledge acquisition

No Comments

No Known Activations