INDEX

Explanations

phrases enclosed in quotation marks, potentially indicating direct speech or emphasis

oai_token-act-pair · gpt-3.5-turbo

punctuation marks, particularly quotation marks and periods, indicating dialogue or the end of statements

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Shot

-0.71

ĻĤ

-0.64

kw

-0.64

 Shot

-0.63

ensical

-0.63

eka

-0.62

uberty

-0.61

iaries

-0.61

 prenatal

-0.60

Kut

-0.60

POSITIVE LOGITS

0.71

ie

0.70

 (Â£

0.65

Â£

0.64

estone

0.62

piece

0.59

VID

0.59

hoe

0.59

 Whilst

0.57

ãħĭ

0.57

Activations Density 0.051%

phrases enclosed in quotation marks, potentially indicating direct speech or emphasis

punctuation marks, particularly quotation marks and periods, indicating dialogue or the end of statements

No Comments

No Known Activations