INDEX

Explanations

phrases related to effectiveness or capability

oai_token-act-pair · gpt-3.5-turbo

phrases and verbs indicating actions that can accomplish tasks or achieve results

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

clus

-0.65

ennett

-0.62

 pursued

-0.61

 Timeline

-0.59

Nas

-0.58

rained

-0.58

LIA

-0.58

 Authority

-0.57

 reinvest

-0.57

ibliography

-0.57

POSITIVE LOGITS

 suffice

1.07

 wonders

0.90

 nicely

0.75

 chores

0.73

ozy

0.72

 havoc

0.72

 trick

0.71

dmg

0.71

job

0.69

 miracles

0.68

Activations Density 0.281%

phrases related to effectiveness or capability

phrases and verbs indicating actions that can accomplish tasks or achieve results

No Comments

No Known Activations