INDEX

Explanations

technical terms related to locations or organizations, potentially with unique identifiers such as codes or numbers

oai_token-act-pair · gpt-3.5-turbo

phrases related to digital content creation or sharing

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

 Canaver

-0.77

THR

-0.71

 Pigs

-0.71

swer

-0.70

ĸļ

-0.69

Hog

-0.69

ovember

-0.69

chy

-0.68

tha

-0.68

emis

-0.67

POSITIVE LOGITS

Runtime

0.87

Latest

0.81

Appearances

0.77

Subject

0.75

Member

0.74

isine

0.72

Topics

0.71

Attributes

0.69

 actionGroup

0.69

notations

0.68

Activations Density 0.063%

technical terms related to locations or organizations, potentially with unique identifiers such as codes or numbers

phrases related to digital content creation or sharing

No Comments

No Known Activations