INDEX

Explanations

words related to keywords or key terms

oai_token-act-pair · gpt-3.5-turbo

terms related to keywords or word usage

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

ocr

-0.82

ocrat

-0.76

asio

-0.75

ramid

-0.73

IDES

-0.71

uci

-0.68

ocratic

-0.67

ocal

-0.66

ocrats

-0.66

oka

-0.65

POSITIVE LOGITS

ptr

1.07

word

0.96

words

0.90

press

0.79

naire

0.79

sworth

0.75

mith

0.74

book

0.73

pedia

0.73

mask

0.71

Activations Density 0.005%

words related to keywords or key terms

terms related to keywords or word usage

No Comments

No Known Activations