INDEX

Explanations

words related to interactions or relationships between different entities

oai_token-act-pair · gpt-3.5-turbo

instances of the word "inter" 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 peanuts

-0.60

awaru

-0.60

 refuge

-0.58

 blindly

-0.58

 Rush

-0.58

 promot

-0.57

 shake

-0.57

ilts

-0.56

 Chaser

-0.56

 payday

-0.56

POSITIVE LOGITS

stitial

1.29

locking

1.28

continental

1.28

racial

1.28

lude

1.27

disciplinary

1.25

dimensional

1.21

cession

1.12

linked

1.11

iors

1.11

Activations Density 0.013%

words related to interactions or relationships between different entities

instances of the word "inter" in various contexts

No Comments

No Known Activations