INDEX

Explanations

dates or time periods

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate historical timelines or origins

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

uliffe

-0.76

ructose

-0.73

eton

-0.71

peat

-0.69

igue

-0.68

è»

-0.67

iband

-0.67

ersen

-0.66

 allowances

-0.65

espie

-0.65

POSITIVE LOGITS

 centuries

0.74

 millennia

0.71

 historically

0.71

 prehistoric

0.71

0.68

0.66

 compr

0.66

 longest

0.66

 decades

0.66

Activations Density 0.092%

dates or time periods

phrases that indicate historical timelines or origins

No Comments

No Known Activations