INDEX

Explanations

instances of technical terms or jargon

oai_token-act-pair · gpt-3.5-turbo

occurrences of a particular character or symbol that appears frequently, likely representing a specific concept or term within the context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 mathemat

-0.76

 Palestin

-0.69

 sacrific

-0.68

 Seym

-0.68

 unden

-0.67

ammy

-0.65

 princ

-0.65

 seiz

-0.64

 proport

-0.64

 Tanz

-0.64

POSITIVE LOGITS

ï¸ı

1.09

ual

0.74

Â£

0.71

own

0.71

eric

0.70

advertisement

0.69

ery

0.69

head

0.69

UAL

0.68

Activations Density 0.189%

instances of technical terms or jargon

occurrences of a particular character or symbol that appears frequently, likely representing a specific concept or term within the context

No Comments

No Known Activations