INDEX

Explanations

words related to Apple products, especially iPhones and iPods

oai_token-act-pair · gpt-3.5-turbo

references to various models of iPhones and iPods

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

é¾

-0.82

rans

-0.81

 Worcester

-0.72

tan

-0.69

holm

-0.69

 externalToEVAOnly

-0.67

tainment

-0.66

sted

-0.65

bil

-0.65

rue

-0.64

POSITIVE LOGITS

 Simulator

0.90

iPhone

0.86

 Safari

0.85

iOS

0.84

 iPad

0.83

 iPhone

0.82

 iCloud

0.78

 MacBook

0.77

 phones

0.77

 iPhones

0.77

Activations Density 0.010%

words related to Apple products, especially iPhones and iPods

references to various models of iPhones and iPods

No Comments

No Known Activations