INDEX

Explanations

expressions related to taking actions or making decisions

oai_token-act-pair · gpt-3.5-turbo

expressions of desire or intent

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

 organised

-0.94

 favourite

-0.89

 favoured

-0.88

 colourful

-0.80

 practise

-0.79

 util

-0.79

 organise

-0.78

 recognised

-0.76

 travellers

-0.75

 pract

-0.75

POSITIVE LOGITS

âĢ

1.15

[/

1.12

âĶ

1.12

----

1.07

âĻ¦

1.06

 âĢ

1.04

--

0.99

**

0.97

––

0.96

-|

0.95

Activations Density 0.669%

expressions related to taking actions or making decisions

expressions of desire or intent

No Comments

No Known Activations