INDEX

Explanations

words related to research and analysis processes

oai_token-act-pair · gpt-3.5-turbo

references to testing procedures and evaluations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

justice

-0.77

joining

-0.71

lance

-0.69

taboola

-0.66

illard

-0.64

ACP

-0.63

yip

-0.62

wikipedia

-0.62

obi

-0.62

ĺħ

-0.61

POSITIVE LOGITS

osterone

1.16

imony

1.13

 conducted

1.02

udo

0.93

 labs

0.90

 laboratories

0.85

 performed

0.82

imon

0.82

 undertaken

0.78

rador

0.76

Activations Density 0.035%

words related to research and analysis processes

references to testing procedures and evaluations

No Comments

No Known Activations