INDEX

Explanations

phrases related to commenting or drawing attention to something

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "something" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

ortex

-0.72

inders

-0.71

awar

-0.70

ardi

-0.70

phones

-0.69

 Examiner

-0.66

DOS

-0.66

anism

-0.65

 Chiefs

-0.64

oret

-0.64

POSITIVE LOGITS

 else

1.39

Else

1.38

 resembling

1.04

 Else

0.87

 worthwhile

0.86

 miraculous

0.83

 intangible

0.80

 happened

0.79

 unheard

0.79

else

0.79

Activations Density 0.047%

phrases related to commenting or drawing attention to something

occurrences of the word "something" in various contexts

No Comments

No Known Activations