INDEX

Explanations

words related to movement and physical locations

oai_token-act-pair · gpt-3.5-turbo

conjunctions and phrases indicating direction or movement

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

uty

-0.62

ANC

-0.61

ulner

-0.61

UF

-0.61

cil

-0.59

actionDate

-0.59

piration

-0.59

dozen

-0.58

 Plans

-0.58

Fight

-0.57

POSITIVE LOGITS

 into

1.63

 onto

1.60

into

1.44

 INTO

1.38

 thence

1.36

 Into

1.31

 onward

1.27

 toward

1.26

 onwards

1.21

 towards

1.17

Activations Density 0.246%

words related to movement and physical locations

conjunctions and phrases indicating direction or movement

No Comments

No Known Activations