INDEX

Explanations

phrases related to announcements or declarations

oai_token-act-pair · gpt-3.5-turbo

instances of the word "announced" and closely related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 subsistence

-0.71

ajo

-0.71

mare

-0.69

 extreme

-0.66

 extremes

-0.64

 temper

-0.63

wer

-0.61

 bush

-0.60

 caution

-0.59

 capital

-0.59

POSITIVE LOGITS

by

0.74

ynamic

0.73

});

0.71

ãĥ¼ãĥĨ

0.71

isSpecialOrderable

0.69

ission

0.69

AAF

0.67

à¼

0.66

daq

0.66

 unanimously

0.66

Activations Density 0.184%

phrases related to announcements or declarations

instances of the word "announced" and closely related terms

No Comments

No Known Activations