INDEX

Explanations

sentences describing people's actions or states

oai_token-act-pair · gpt-3.5-turbo

phrases indicating the presence and actions of people

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

xxxx

-0.76

 predecessor

-0.69

achment

-0.68

TX

-0.65

 srfAttach

-0.63

imental

-0.63

ONSORED

-0.63

verse

-0.63

 saga

-0.62

 fiasco

-0.61

POSITIVE LOGITS

 clam

1.09

 understandably

0.95

ateurs

0.95

 alike

0.93

 accustomed

0.91

 beware

0.90

 routinely

0.90

 eager

0.87

 everywhere

0.84

 encouraged

0.83

Activations Density 0.388%

sentences describing people's actions or states

phrases indicating the presence and actions of people

No Comments

No Known Activations