INDEX

Explanations

timeframes expressed in relation to the past

oai_token-act-pair · gpt-3.5-turbo

phrases indicating approximate time durations or intervals

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

rawdownloadcloneembedreportprint

-0.85

advertisement

-0.76

RP

-0.73

sheet

-0.72

ForgeModLoader

-0.69

uction

-0.68

BALL

-0.67

Mods

-0.66

ADVERTISEMENT

-0.66

DNA

-0.65

POSITIVE LOGITS

 onwards

0.83

 onward

0.78

 counting

0.73

 oranges

0.72

yea

0.67

 breadth

0.66

fw

0.65

 trave

0.63

 gestation

0.63

 harvest

0.63

Activations Density 0.194%

timeframes expressed in relation to the past

phrases indicating approximate time durations or intervals

No Comments

No Known Activations