INDEX

Explanations

specific groups of entities mentioned in the text

oai_token-act-pair · gpt-3.5-turbo

references to groups or entities being discussed 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 @ 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 unden

-0.66

éŃĶ

-0.63

 instead

-0.61

 sometime

-0.60

çī

-0.59

 shortly

-0.59

 earthqu

-0.56

 unfinished

-0.56

rus

-0.56

 Dimension

-0.56

POSITIVE LOGITS

 ever

1.47

nor

1.38

 EVER

1.32

 dared

1.25

 bothered

1.22

ever

1.22

 survives

1.15

 whatsoever

1.15

 mattered

1.12

 necessarily

1.11

Activations Density 0.237%

specific groups of entities mentioned in the text

references to groups or entities being discussed in various contexts

No Comments

No Known Activations