INDEX

Explanations

personal pronouns 'you' or 'yourself' asking for opinions or thoughts

oai_token-act-pair · gpt-3.5-turbo

questions directed at the audience seeking opinions or thoughts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

abad

-0.77

viol

-0.68

 Izan

-0.67

atural

-0.66

 Travels

-0.64

Journal

-0.63

ocol

-0.61

Lago

-0.61

 Hels

-0.60

enges

-0.58

POSITIVE LOGITS

 think

1.08

 reckon

1.07

 guys

1.07

 propose

0.88

 suppose

0.86

say

0.79

 mean

0.78

 thoughts

0.78

 expect

0.76

 decide

0.75

Activations Density 0.057%

personal pronouns 'you' or 'yourself' asking for opinions or thoughts

questions directed at the audience seeking opinions or thoughts

No Comments

No Known Activations