INDEX

Explanations

names or phrases starting with "Let" followed by a relatively high score

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "let" in various contexts

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

 cumbers

-0.70

 holiest

-0.68

foreseen

-0.63

liest

-0.63

nown

-0.61

omething

-0.61

imposed

-0.58

 Sins

-0.57

externalActionCode

-0.55

BLE

-0.55

POSITIVE LOGITS

tered

1.31

icia

1.11

itia

1.10

tering

1.10

ters

1.08

ting

1.01

istical

0.87

cheon

0.83

 loose

0.81

downs

0.78

Activations Density 0.026%

names or phrases starting with "Let" followed by a relatively high score

occurrences of the word "let" in various contexts

No Comments

No Known Activations