INDEX

Explanations

words describing various stages of a process or situation

oai_token-act-pair · gpt-3.5-turbo

references to specific stages or points in a discussion or process

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

 flyers

-0.78

 warranties

-0.67

 lovers

-0.66

 masc

-0.62

 inspir

-0.61

nap

-0.61

 viol

-0.60

 Fighters

-0.60

 compuls

-0.58

Choice

-0.58

POSITIVE LOGITS

ajor

0.80

 onwards

0.78

cture

0.77

isphere

0.74

 onward

0.72

abouts

0.70

ature

0.69

cano

0.69

imester

0.68

ZI

0.68

Activations Density 0.041%

words describing various stages of a process or situation

references to specific stages or points in a discussion or process

No Comments

No Known Activations