INDEX

Explanations

references to numbers or statistics

oai_token-act-pair · gpt-3.5-turbo

references to actions and events related to conflict or disruptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

etc

-0.61

 respectively

-0.58

'.

-0.58

 thereto

-0.57

*.

-0.53

 accordingly

-0.53

.).

-0.53

).[

-0.52

".

-0.50

+.

-0.50

POSITIVE LOGITS

vez

0.50

endon

0.45

romeda

0.44

namese

0.43

rad

0.40

buquerque

0.39

different

0.38

illance

0.38

oug

0.38

ridor

0.38

Activations Density 2.666%

references to numbers or statistics

references to actions and events related to conflict or disruptions

No Comments

No Known Activations