INDEX

Explanations

references to technology and brand names

oai_token-act-pair · gpt-3.5-turbo

patterns and relationships related to quantity or comparison

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

ocious

-0.60

ustainable

-0.56

evidence

-0.55

icipated

-0.55

ynamic

-0.54

ormal

-0.54

lycer

-0.53

 pend

-0.53

iked

-0.53

cohol

-0.53

POSITIVE LOGITS

merce

0.57

Bin

0.53

 blah

0.52

 Stout

0.50

Bam

0.50

 Cinema

0.49

 Uncharted

0.48

 theirs

0.48

 lockdown

0.48

wings

0.47

Activations Density 1.394%

references to technology and brand names

patterns and relationships related to quantity or comparison

No Comments

No Known Activations