INDEX

Explanations

terms related to "Bologna" or "ology."

oai_token-act-pair · gpt-3.5-turbo

terms related to various fields of study or disciplines

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

awar

-0.77

arnaev

-0.71

noon

-0.68

theless

-0.67

flies

-0.66

affe

-0.65

IELD

-0.64

leep

-0.62

bare

-0.62

 STATES

-0.61

POSITIVE LOGITS

ues

1.49

gers

1.09

uez

1.07

uing

1.07

UE

1.06

ued

1.05

rams

1.03

raphic

0.95

ging

0.94

uish

0.93

Activations Density 0.091%

terms related to "Bologna" or "ology."

terms related to various fields of study or disciplines

No Comments

No Known Activations