INDEX

Explanations

questions about the meaning or significance of something

oai_token-act-pair · gpt-3.5-turbo

phrases questioning the meaning of a concept or situation

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

ttes

-0.74

tions

-0.68

 Pend

-0.67

visors

-0.66

visor

-0.66

 diversion

-0.64

Du

-0.62

 Paso

-0.62

tk

-0.62

Toy

-0.61

POSITIVE LOGITS

rawdownloadcloneembedreportprint

0.77

ELL

0.71

INGS

0.68

terday

0.66

pling

0.66

 goodbye

0.65

 depends

0.64

agall

0.64

Ð»

0.64

?:

0.63

Activations Density 0.019%

questions about the meaning or significance of something

phrases questioning the meaning of a concept or situation

No Comments

No Known Activations