INDEX

Explanations

detailed descriptions of events or situations involving multiple entities

oai_token-act-pair · gpt-3.5-turbo

phrases indicating realization or unexpected events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

''.

-0.65

 respectively

-0.63

)).

-0.61

.ï¿½

-0.60

anwhile

-0.57

.).

-0.57

`.

-0.52

]."

-0.52

.''.

-0.52

}.

-0.52

POSITIVE LOGITS

anity

0.40

 Twitter

0.38

 tweet

0.38

blog

0.37

byn

0.36

aph

0.36

 livestream

0.36

 Guant

0.35

 Pepe

0.35

 pige

0.35

Activations Density 3.135%

detailed descriptions of events or situations involving multiple entities

phrases indicating realization or unexpected events

No Comments

No Known Activations