INDEX

Explanations

instances of "for the first time in" phrases

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate significant temporal milestones or first occurrences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

dan

-0.66

$$$$

-0.65

bos

-0.64

rox

-0.63

 handsome

-0.62

#$

-0.62

mil

-0.61

 resemb

-0.60

 ILCS

-0.60

bec

-0.60

POSITIVE LOGITS

clusively

0.98

 succession

0.85

patient

0.84

operative

0.83

0.80

accessible

0.79

efficiency

0.79

clusions

0.79

 captivity

0.78

 conjunction

0.77

Activations Density 0.087%

instances of "for the first time in" phrases

phrases that indicate significant temporal milestones or first occurrences

No Comments

No Known Activations