INDEX

Explanations

phrases indicating a desire or request for information or action

oai_token-act-pair · gpt-3.5-turbo

phrases that express desire or requests for information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

livious

-0.63

 wounding

-0.63

 Olympia

-0.57

 Reconstruction

-0.57

 Tosh

-0.55

 Reflect

-0.54

 obser

-0.54

 Emanuel

-0.54

 injuring

-0.54

rup

-0.54

POSITIVE LOGITS

reprene

1.13

only

1.00

zens

0.83

agh

0.81

on

0.76

gotten

0.76

zin

0.75

atile

0.73

anta

0.72

htar

0.72

Activations Density 0.044%

phrases indicating a desire or request for information or action

phrases that express desire or requests for information

No Comments

No Known Activations