INDEX

Explanations

verbs related to taking action or influencing a situation

oai_token-act-pair · gpt-3.5-turbo

actions related to promoting, establishing, or enhancing various efforts or initiatives

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

Downloadha

-0.76

arij

-0.73

option

-0.67

Fax

-0.66

-----------

-0.65

pmwiki

-0.64

NetMessage

-0.63

never

-0.62

sbm

-0.62

Ago

-0.62

POSITIVE LOGITS

uate

0.77

veland

0.73

 amplify

0.67

burse

0.67

escape

0.65

 paternity

0.62

 digestion

0.62

etch

0.62

 snowball

0.60

 budding

0.59

Activations Density 0.133%

verbs related to taking action or influencing a situation

actions related to promoting, establishing, or enhancing various efforts or initiatives

No Comments

No Known Activations