INDEX

Explanations

instances where the word "you" is used with a high emphasis or importance

oai_token-act-pair · gpt-3.5-turbo

references to the second person in rhetorical 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

inki

-0.66

furt

-0.64

hurst

-0.63

ifacts

-0.62

Net

-0.61

icio

-0.61

NOT

-0.60

Vers

-0.59

ington

-0.58

gypt

-0.57

POSITIVE LOGITS

 anymore

0.82

kered

0.77

afe

0.68

dfx

0.65

 ashamed

0.65

 whatsoever

0.65

 pity

0.63

 appe

0.62

 dare

0.62

?!

0.60

Activations Density 0.079%

instances where the word "you" is used with a high emphasis or importance

references to the second person in rhetorical questions

No Comments

No Known Activations