INDEX

Explanations

phrases related to instructions or steps

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate a method or way to achieve something

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 pains

-0.70

 notices

-0.66

thal

-0.65

alty

-0.64

 particulars

-0.63

 acknowled

-0.62

 havoc

-0.60

Ily

-0.58

iannopoulos

-0.58

ality

-0.58

POSITIVE LOGITS

 simply

0.74

\\\\\\\\

0.74

 through

0.67

 relying

0.65

©¶æ

0.65

Simply

0.64

Simple

0.63

 utilizing

0.63

guided

0.63

through

0.62

Activations Density 0.173%

phrases related to instructions or steps

phrases that indicate a method or way to achieve something

No Comments

No Known Activations