INDEX

Explanations

phrases related to things being powered or run by various technologies

oai_token-act-pair · gpt-3.5-turbo

terms related to power and energy sources

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ordan

-0.87

esan

-0.83

algia

-0.76

edi

-0.76

oral

-0.71

roma

-0.71

ylum

-0.69

istani

-0.69

ynski

-0.68

esi

-0.67

POSITIVE LOGITS

 powered

0.86

powered

0.78

ups

0.75

 wheelchair

0.71

 Powered

0.70

ups

0.70

PDATE

0.70

wagen

0.70

packs

0.70

 powering

0.70

Activations Density 0.024%

phrases related to things being powered or run by various technologies

terms related to power and energy sources

No Comments

No Known Activations