INDEX

Explanations

specific characters or symbols

oai_token-act-pair · gpt-3.5-turbo

punctuation marks and formatting in the text

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

 orbiting

-0.75

zbollah

-0.74

apons

-0.73

 disapprove

-0.72

 disappro

-0.71

phia

-0.71

 Saiyan

-0.71

 contempl

-0.70

 droid

-0.69

ushima

-0.68

POSITIVE LOGITS

READ

0.99

CBC

0.97

gary

0.84

Adding

0.83

However

0.82

Cr

0.82

Some

0.82

Mont

0.81

Statistics

0.81

Those

0.81

Activations Density 0.381%

specific characters or symbols

punctuation marks and formatting in the text

No Comments

No Known Activations