INDEX

Explanations

terms related to "semi-" or "semiautomatic."

oai_token-act-pair · gpt-3.5-turbo

phrases related to semi-automatic firearms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

bats

-0.83

HCR

-0.75

çĦ

-0.74

 guts

-0.72

 Merchants

-0.70

 DRAG

-0.69

 Tycoon

-0.68

IRO

-0.68

flies

-0.67

ORE

-0.67

POSITIVE LOGITS

eteen

0.93

lethal

0.88

ature

0.87

cedes

0.84

©¶æ

0.78

arily

0.78

atural

0.78

cient

0.77

quel

0.77

otin

0.76

Activations Density 0.008%

terms related to "semi-" or "semiautomatic."

phrases related to semi-automatic firearms

No Comments

No Known Activations