INDEX

Explanations

numerical values representing statistics or measurements

oai_token-act-pair · gpt-3.5-turbo

numerical data or statistics

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

ependence

-0.69

entimes

-0.63

 embargo

-0.61

ESE

-0.61

ulate

-0.60

ulatory

-0.59

esa

-0.59

urer

-0.58

 footing

-0.58

 crunch

-0.57

POSITIVE LOGITS

MSN

1.13

 Rated

0.76

phot

0.73

å¸

0.71

éĹĺ

0.69

Downloadha

0.67

rawdownloadcloneembedreportprint

0.67

0.66

å§«

0.66

tiny

0.66

Activations Density 0.277%

numerical values representing statistics or measurements

numerical data or statistics

No Comments

No Known Activations