INDEX

Explanations

references to individual people or entities

oai_token-act-pair · gpt-3.5-turbo

references to organizational or administrative divisions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

 tampering

-0.55

 Predators

-0.54

RELATED

-0.53

 Buddy

-0.52

endez

-0.48

 cannibal

-0.48

 bonding

-0.48

 Carnage

-0.48

Monster

-0.47

 craz

-0.47

POSITIVE LOGITS

 keynote

0.69

 quotations

0.67

 Nobel

0.65

 parliament

0.64

 organis

0.63

 philosophers

0.61

 parliamentary

0.60

 philosopher

0.58

 emphas

0.57

 essays

0.57

Activations Density 2.282%

references to individual people or entities

references to organizational or administrative divisions

No Comments

No Known Activations