INDEX

Explanations

words related to objects or concepts of interest or potential importance

oai_token-act-pair · gpt-3.5-turbo

terms related to monitoring and security when discussing environments and situations

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

ortment

-0.66

rongh

-0.63

levision

-0.60

enhagen

-0.58

 Bowen

-0.57

ASA

-0.57

ggles

-0.56

eg

-0.56

Fig

-0.56

mma

-0.56

POSITIVE LOGITS

 whatsoever

1.56

nor

1.47

 anymore

1.35

 slightest

0.91

 anywhere

0.87

 except

0.87

 anybody

0.82

 bothered

0.79

 markings

0.79

nor

0.78

Activations Density 0.317%

words related to objects or concepts of interest or potential importance

terms related to monitoring and security when discussing environments and situations

No Comments

No Known Activations