INDEX

Explanations

terms related to numbers and quantities

oai_token-act-pair · gpt-3.5-turbo

numeric data and statistics

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

Scene

-0.54

Spoiler

-0.51

Kus

-0.49

 Disclosure

-0.49

ESA

-0.49

Gou

-0.47

Artist

-0.47

 ASAP

-0.47

 Transparency

-0.47

 Problems

-0.47

POSITIVE LOGITS

 menstru

0.66

 respectively

0.66

 tert

0.62

 sexes

0.59

 depending

0.59

 intermediate

0.58

 equivalents

0.57

 retirees

0.56

 specialize

0.56

ngth

0.56

Activations Density 1.515%

terms related to numbers and quantities

numeric data and statistics

No Comments

No Known Activations