INDEX

Explanations

words that are in the past tense

oai_token-act-pair · gpt-3.5-turbo

past and present participle verbs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

imet

-0.75

ses

-0.74

schild

-0.74

orest

-0.73

sis

-0.72

 pots

-0.69

 stomp

-0.67

imeters

-0.67

yz

-0.67

ivari

-0.66

POSITIVE LOGITS

 Releases

0.79

fleet

0.78

 Lists

0.71

 Modes

0.71

 Freak

0.70

 Hilbert

0.70

 Officer

0.68

 Torrent

0.68

 Celeb

0.67

 Charity

0.66

Activations Density 0.119%

words that are in the past tense

past and present participle verbs

No Comments

No Known Activations