INDEX

Explanations

acronyms and codes

oai_token-act-pair · gpt-3.5-turbo

data or figures related to statistics and performance metrics

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

phrine

-0.93

nings

-0.68

glers

-0.66

naissance

-0.66

atche

-0.66

ĪĴ

-0.63

essor

-0.63

Owl

-0.59

hift

-0.58

tery

-0.58

POSITIVE LOGITS

ieu

0.69

ãĤ¤ãĥĪ

0.67

shown

0.66

roman

0.65

aden

0.64

luster

0.62

ittal

0.60

gage

0.60

igham

0.59

arters

0.59

Activations Density 0.305%

acronyms and codes

data or figures related to statistics and performance metrics

No Comments

No Known Activations