INDEX

Explanations

phrases starting with "Not so" and "Much"

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate a negation or contradiction

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

ãĥ¼ãĥĨãĤ£

-0.76

ãĤ¼ãĤ¦ãĤ¹

-0.66

MAP

-0.63

 DRAGON

-0.59

idential

-0.57

 SHARES

-0.57

 Places

-0.56

 Unable

-0.56

Maps

-0.56

{:

-0.55

POSITIVE LOGITS

 anymore

0.89

 much

0.88

ppy

0.83

othes

0.80

apy

0.80

imilar

0.76

oths

0.74

igne

0.71

aked

0.71

oooo

0.71

Activations Density 0.040%

phrases starting with "Not so" and "Much"

phrases that indicate a negation or contradiction

No Comments

No Known Activations