INDEX

Explanations

verbs related to dependency or causation

oai_token-act-pair · gpt-3.5-turbo

phrases that express dependency or conditionality

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

ugu

-0.58

thia

-0.56

MQ

-0.56

weeney

-0.53

ujah

-0.52

 mosqu

-0.51

 Supports

-0.51

 cabinets

-0.50

ngth

-0.50

aughtered

-0.50

POSITIVE LOGITS

 murky

0.58

 stark

0.57

\\\\\\\\

0.56

VPN

0.56

IER

0.56

 obfusc

0.55

 palp

0.55

hidden

0.54

 muted

0.54

PLIC

0.53

Activations Density 1.116%

verbs related to dependency or causation

phrases that express dependency or conditionality

No Comments

No Known Activations