INDEX

Explanations

numerical values and measurements

oai_token-act-pair · gpt-3.5-turbo

quantifiable measurements or numeric data 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 @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

olas

-0.79

visors

-0.77

acers

-0.74

Names

-0.73

ramids

-0.72

 Secrets

-0.72

apses

-0.72

reads

-0.72

Sym

-0.72

iers

-0.71

POSITIVE LOGITS

 supra

0.98

 multi

0.95

 ultra

0.87

 quasi

0.86

 minimalist

0.84

independent

0.83

 pseudo

0.83

 semi

0.83

 nonpartisan

0.79

non

0.78

Activations Density 0.194%

numerical values and measurements

quantifiable measurements or numeric data in various contexts

No Known Activations