INDEX

Explanations

proper nouns related to various topics, such as movies, novels, and current events

oai_token-act-pair · gpt-3.5-turbo

references to titles and names, particularly in a fictional or entertainment context

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

avorite

-0.77

osite

-0.62

 Guatem

-0.61

 Weston

-0.56

anwhile

-0.55

expensive

-0.55

 surv

-0.55

alus

-0.55

 Winc

-0.53

oided

-0.53

POSITIVE LOGITS

Â»

1.92

âĢ

1.84

[/

1.82

ãĢį

1.57

 âĢ

1.51

]'

1.49

ãĢ

1.49

**

1.47

</

1.45

1.42

Activations Density 0.827%

proper nouns related to various topics, such as movies, novels, and current events

references to titles and names, particularly in a fictional or entertainment context

No Comments

No Known Activations