INDEX

Explanations

phrases related to news articles or blog posts

oai_token-act-pair · gpt-3.5-turbo

punctuation marks, particularly commas

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

================================================================

-0.62

 Masquerade

-0.61

robe

-0.58

wards

-0.58

 =================================================================

-0.57

ieri

-0.55

 Dempsey

-0.53

_>

-0.53

 âĢķ

-0.52

eco

-0.50

POSITIVE LOGITS

»Ĵ

0.69

available

0.67

adapt

0.67

ãĥīãĥ©

0.64

©¶æ

0.63

ounce

0.61

aditional

0.60

ounced

0.59

ä

0.58

igg

0.58

Activations Density 0.084%

phrases related to news articles or blog posts

punctuation marks, particularly commas

No Comments

No Known Activations