INDEX

Explanations

terms related to branding and sponsored content

oai_token-act-pair · gpt-3.5-turbo

references to branding and branded products

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

pmwiki

-0.81

vati

-0.76

isite

-0.71

hower

-0.71

abama

-0.66

rouch

-0.66

veyard

-0.65

ulhu

-0.63

 WARN

-0.63

ippi

-0.63

POSITIVE LOGITS

ovan

0.94

 branding

0.90

 branded

0.88

 loyalty

0.87

ging

0.86

Brand

0.84

brand

0.77

ounce

0.76

uine

0.74

mint

0.73

Activations Density 0.016%

terms related to branding and sponsored content

references to branding and branded products

No Comments

No Known Activations