INDEX

Explanations

phrases related to technology products and company names

oai_token-act-pair · gpt-3.5-turbo

references to specific brands or 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

ailable

-0.83

ailability

-0.82

ensical

-0.73

 citiz

-0.67

 pestic

-0.67

 horizon

-0.66

tenance

-0.63

 deaf

-0.61

ĪĴ

-0.61

 doorstep

-0.61

POSITIVE LOGITS

agall

0.93

espie

0.84

utra

0.77

ppe

0.70

reau

0.69

veland

0.67

esome

0.66

igers

0.65

anamo

0.65

 Sheen

0.65

Activations Density 0.689%

phrases related to technology products and company names

references to specific brands or products

No Comments

No Known Activations