INDEX

Explanations

phrases indicating factual information or discussions

oai_token-act-pair · gpt-3.5-turbo

negative or uncertain statements and their consequences

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

ONSORED

-0.62

 viability

-0.58

 theirs

-0.57

Similarly

-0.57

 consequ

-0.57

 thereof

-0.56

 beforehand

-0.56

 unaffected

-0.56

liner

-0.56

/"

-0.56

POSITIVE LOGITS

eeee

0.69

reetings

0.69

 Joined

0.66

eah

0.65

 Bought

0.65

 thee

0.64

!--

0.63

 awoke

0.63

 Vegan

0.63

 LOVE

0.62

Activations Density 0.554%

phrases indicating factual information or discussions

negative or uncertain statements and their consequences

No Comments

No Known Activations