INDEX

Explanations

technical terms and jargon related to various fields of study

oai_token-act-pair · gpt-3.5-turbo

terms related to scientific concepts and phenomena

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

stals

-0.76

 IMAGES

-0.74

amins

-0.71

iences

-0.69

 Commodore

-0.69

ovies

-0.68

 Forums

-0.68

rils

-0.67

yrights

-0.67

ses

-0.65

POSITIVE LOGITS

 causation

0.99

 versus

0.96

 exhaustion

0.94

 fallacy

0.94

 neutrality

0.93

iosis

0.92

 substitution

0.91

 depletion

0.88

 convergence

0.88

 mismatch

0.87

Activations Density 0.338%

technical terms and jargon related to various fields of study

terms related to scientific concepts and phenomena

No Comments

No Known Activations