INDEX

Explanations

phrases related to potential consequences or outcomes of various situations and actions

oai_token-act-pair · gpt-3.5-turbo

conditional statements related to potential future outcomes or 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 amazed

-0.66

 Annotations

-0.65

ecause

-0.59

pecially

-0.59

ighters

-0.59

ictionary

-0.57

 Occasionally

-0.57

+++

-0.57

 contrasts

-0.56

 rarely

-0.56

POSITIVE LOGITS

 tomorrow

0.97

 someday

0.80

mission

0.69

 sufficiently

0.68

 next

0.66

ansion

0.65

 hereafter

0.64

 enough

0.63

 correctly

0.63

enough

0.62

Activations Density 0.241%

phrases related to potential consequences or outcomes of various situations and actions

conditional statements related to potential future outcomes or consequences

No Comments

No Known Activations