INDEX

Explanations

instances where something is described as happening more or less than what was anticipated or expected

oai_token-act-pair · gpt-3.5-turbo

phrases related to expectations and anticipations in various contexts

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

yna

-0.71

vl

-0.70

ona

-0.68

obal

-0.68

guyen

-0.67

abases

-0.67

istries

-0.65

enberg

-0.65

icy

-0.64

umbn

-0.63

POSITIVE LOGITS

 hinges

0.76

aneously

0.68

 Targ

0.68

 realizes

0.67

 acknowledges

0.67

 therap

0.66

.","

0.65

 expectations

0.64

 estim

0.62

due

0.61

Activations Density 0.070%

instances where something is described as happening more or less than what was anticipated or expected

phrases related to expectations and anticipations in various contexts

No Comments

No Known Activations