INDEX

Explanations

non-English characters and symbols

oai_token-act-pair · gpt-3.5-turbo

symbols and punctuation marks used in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 colours

-0.56

 maths

-0.53

 flavours

-0.52

 tyres

-0.52

 practise

-0.52

 flavour

-0.51

 symbols

-0.50

 cafes

-0.49

 behaviour

-0.49

 veins

-0.48

POSITIVE LOGITS

percent

0.59

bernatorial

0.58

tie

0.54

conserv

0.54

¥

0.50

vantage

0.50

imon

0.49

berto

0.49

owship

0.49

ajor

0.48

Activations Density 1.919%

non-English characters and symbols

symbols and punctuation marks used in various contexts

No Comments

No Known Activations