INDEX

Explanations

personal pronouns indicating the subject as "I" or "we" in questions and statements

oai_token-act-pair · gpt-3.5-turbo

the plural pronoun "we" and its variants in questions

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

 Flavoring

-0.81

bnb

-0.67

roups

-0.66

edIn

-0.66

 Cutting

-0.66

-+

-0.66

uces

-0.65

ãĤ¦ãĤ¹

-0.64

 srfAttach

-0.64

 Conversation

-0.64

POSITIVE LOGITS

 intend

0.96

 presume

0.88

 think

0.85

 dare

0.85

 deserve

0.84

 pretend

0.81

 reckon

0.80

 expect

0.79

 aspire

0.79

 recognise

0.78

Activations Density 0.056%

personal pronouns indicating the subject as "I" or "we" in questions and statements

the plural pronoun "we" and its variants in questions

No Comments

No Known Activations