INDEX

Explanations

prepositions indicating direction or position, vehicles, and ways of investigation

oai_token-act-pair · gpt-3.5-turbo

phrases indicating movement or direction

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

 justifies

-0.64

avier

-0.63

 quot

-0.62

 Compan

-0.61

 ounce

-0.61

":[

-0.60

 intimid

-0.60

 compromises

-0.59

 interacts

-0.58

ifle

-0.58

POSITIVE LOGITS

now

0.84

going

0.82

currently

0.82

joice

0.79

 underway

0.77

 ready

0.73

ready

0.72

NOW

0.71

 primed

0.69

 waiting

0.69

Activations Density 0.372%

prepositions indicating direction or position, vehicles, and ways of investigation

phrases indicating movement or direction

No Comments

No Known Activations