INDEX

Explanations

phrases related to hypothetical situations or conditions

oai_token-act-pair · gpt-3.5-turbo

phrases expressing hypothetical scenarios 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 @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

 disclaimer

-0.70

DOC

-0.64

 outline

-0.63

UL

-0.62

cius

-0.59

 intangible

-0.59

 scept

-0.58

DOC

-0.57

 clarify

-0.56

 reminder

-0.55

POSITIVE LOGITS

schild

0.93

 bothered

0.83

 mattered

0.82

 anymore

0.78

oppers

0.74

nor

0.73

 necessarily

0.71

ajor

0.69

icable

0.68

 tolerated

0.68

Activations Density 0.122%

phrases related to hypothetical situations or conditions

phrases expressing hypothetical scenarios and their consequences

No Comments

No Known Activations