INDEX

Explanations

words related to locks and securing things

oai_token-act-pair · gpt-3.5-turbo

references to locking mechanisms and security systems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

resso

-0.77

LV

-0.71

issance

-0.64

popular

-0.63

 Eleven

-0.63

ãĤ¡

-0.62

PsyNetMessage

-0.60

ANI

-0.60

opausal

-0.60

aced

-0.59

POSITIVE LOGITS

picking

1.21

heed

1.04

pick

1.01

lear

0.87

lock

0.86

 lock

0.84

downs

0.83

creen

0.80

 locks

0.80

 horns

0.76

Activations Density 0.013%

words related to locks and securing things

references to locking mechanisms and security systems

No Comments

No Known Activations