INDEX

Explanations

action words related to gaining or obtaining something

oai_token-act-pair · gpt-3.5-turbo

phrases related to achieving recognition or gaining something

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

hov

-0.71

hal

-0.66

cas

-0.62

hhhh

-0.61

sil

-0.61

andro

-0.60

iazep

-0.59

oooooooooooooooo

-0.57

die

-0.57

upon

-0.56

POSITIVE LOGITS

ãĤ©

0.87

ographs

0.85

eteenth

0.80

OGR

0.78

 garner

0.77

DragonMagazine

0.76

 garnered

0.74

interstitial

0.74

 Pradesh

0.69

 renown

0.68

Activations Density 0.012%

action words related to gaining or obtaining something

phrases related to achieving recognition or gaining something

No Comments

No Known Activations