INDEX

Explanations

prepositional phrases indicating involvement or agency

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "in" and its context or frequency within the text

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

raid

-0.85

wine

-0.81

iris

-0.73

ALSE

-0.71

ratulations

-0.66

AAAAAAAA

-0.66

IDES

-0.65

angered

-0.64

casters

-0.64

RR

-0.63

POSITIVE LOGITS

 regards

1.49

 terms

1.47

 relation

1.40

 determining

1.36

 achieving

1.31

 selecting

1.29

 implementing

1.29

 shaping

1.28

 administering

1.28

 constructing

1.28

Activations Density 0.252%

prepositional phrases indicating involvement or agency

occurrences of the word "in" and its context or frequency within the text

No Comments

No Known Activations