INDEX

Explanations

information related to investigation or examination

oai_token-act-pair · gpt-3.5-turbo

keywords related to research and analysis

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

interstitial

-0.76

Adds

-0.71

 celebrations

-0.68

Delivery

-0.68

YP

-0.67

iru

-0.63

uty

-0.63

UME

-0.62

apo

-0.60

=$

-0.59

POSITIVE LOGITS

 firsthand

0.80

tested

0.79

©¶æ

0.77

 testim

0.75

ritz

0.75

oscope

0.75

ocrates

0.75

 declass

0.74

 microscope

0.74

 carefully

0.73

Activations Density 0.973%

information related to investigation or examination

keywords related to research and analysis

No Comments

No Known Activations