INDEX

Explanations

words related to locks or locking mechanisms

oai_token-act-pair · gpt-3.5-turbo

instances of the word "lock" 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

ional

-0.72

 constitu

-0.71

issance

-0.67

schild

-0.67

OTAL

-0.65

 Legion

-0.65

haps

-0.64

olf

-0.63

ial

-0.62

LV

-0.61

POSITIVE LOGITS

picking

1.37

pick

1.21

heed

1.18

step

1.06

hart

1.06

 horns

1.04

creen

1.02

lear

0.98

yer

0.96

door

0.96

Activations Density 0.035%

words related to locks or locking mechanisms

instances of the word "lock" in various contexts

No Comments

No Known Activations