INDEX

Explanations

phrases or names related to organizations or institutions

oai_token-act-pair · gpt-3.5-turbo

proper nouns or names related to institutions, places, or significant entities

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

retty

-0.83

earances

-0.83

icipated

-0.82

rys

-0.71

reciation

-0.67

itiveness

-0.67

iliary

-0.64

 omega

-0.61

 Freak

-0.61

ologies

-0.59

POSITIVE LOGITS

ipedia

0.76

SourceFile

0.75

Vi

0.71

steen

0.71

Ped

0.67

abis

0.66

ornia

0.65

Cla

0.63

anders

0.62

imaru

0.62

Activations Density 0.206%

phrases or names related to organizations or institutions

proper nouns or names related to institutions, places, or significant entities

No Comments

No Known Activations