INDEX

Explanations

phrases related to features or attributes

oai_token-act-pair · gpt-3.5-turbo

statements indicating significance, intensity, or emphasis in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

irez

-0.71

 vouchers

-0.68

anton

-0.61

usalem

-0.59

 mismatch

-0.58

acion

-0.56

 seminars

-0.56

 Club

-0.56

 Koran

-0.55

azing

-0.55

POSITIVE LOGITS

\\\\\\\\

0.70

Els

0.66

ovie

0.65

ãĤ¢ãĥ«

0.64

Synopsis

0.62

ploy

0.61

SpaceEngineers

0.60

ãĤ®

0.60

\":

0.59

 conce

0.59

Activations Density 1.997%

phrases related to features or attributes

statements indicating significance, intensity, or emphasis in various contexts

No Comments

No Known Activations