INDEX

Explanations

comparative terms indicating quantity or degree

oai_token-act-pair · gpt-3.5-turbo

references to abundance or variety

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

 Quart

-0.71

hower

-0.65

 WARN

-0.62

 Auth

-0.61

witz

-0.60

rison

-0.60

IGHT

-0.58

APTER

-0.58

iew

-0.56

Leaks

-0.56

POSITIVE LOGITS

 assorted

1.03

cellaneous

0.82

Downloadha

0.82

 occasional

0.77

etc

0.74

 importantly

0.72

whatever

0.71

anything

0.68

 general

0.67

 downright

0.67

Activations Density 0.371%

comparative terms indicating quantity or degree

references to abundance or variety

No Comments

No Known Activations