INDEX

Explanations

technical terms related to data processing or organization

oai_token-act-pair · gpt-3.5-turbo

topics related to numerical data and statistical measurements

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

 emailed

-0.74

 sadly

-0.73

 ever

-0.71

 tweeting

-0.71

 recently

-0.70

 tweeted

-0.69

 EVER

-0.69

 shockingly

-0.68

 heartbreaking

-0.68

 wouldn

-0.68

POSITIVE LOGITS

 Functions

1.12

Parameter

1.11

Definition

1.06

 Description

1.06

 Definitions

1.05

 Symbol

1.03

 Classification

1.00

Parameters

0.99

 Types

0.99

 Parameters

0.96

Activations Density 0.331%

technical terms related to data processing or organization

topics related to numerical data and statistical measurements

No Comments

No Known Activations