INDEX

Explanations

the word "sub."

oai_token-act-pair · gpt-3.5-turbo

the frequency of specific syllable patterns or sounds in words

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

 helic

-0.72

 unexplained

-0.72

 suspense

-0.62

iolet

-0.61

erker

-0.60

 concess

-0.58

orks

-0.58

 MÃ©

-0.57

 intens

-0.57

 clocks

-0.56

POSITIVE LOGITS

bery

0.95

bed

0.80

ulent

0.78

bish

0.78

eties

0.75

liest

0.72

ulence

0.68

nit

0.67

lord

0.67

pees

0.66

Activations Density 0.079%

the word "sub."

the frequency of specific syllable patterns or sounds in words

No Comments

No Known Activations