INDEX

Explanations

statistics and numerical information

oai_token-act-pair · gpt-3.5-turbo

quantifiable results or findings from studies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

Contents

-0.81

Edit

-0.78

ographs

-0.72

acid

-0.72

Ask

-0.72

 asks

-0.71

anders

-0.68

ands

-0.68

umi

-0.68

iner

-0.66

POSITIVE LOGITS

 discrepancy

1.31

 resemblance

1.29

 similarity

1.27

 correlation

1.13

 willingness

1.11

 contradiction

1.08

 disparity

1.05

 lack

1.04

 glimpse

1.03

 spike

1.02

Activations Density 0.209%

statistics and numerical information

quantifiable results or findings from studies

No Comments

No Known Activations