INDEX

Explanations

terms related to detailed step-by-step guidance or advice

oai_token-act-pair · gpt-3.5-turbo

references to instructions and guidelines

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

oner

-0.67

culosis

-0.64

itton

-0.63

 plaus

-0.62

stocks

-0.61

vill

-0.61

erenn

-0.60

xious

-0.59

duc

-0.59

olson

-0.59

POSITIVE LOGITS

 manuals

1.04

eering

1.04

Instruct

0.95

 booklet

0.93

 manual

0.91

 Instructions

0.89

 instructions

0.89

 Manual

0.86

auri

0.84

 instruction

0.82

Activations Density 0.031%

terms related to detailed step-by-step guidance or advice

references to instructions and guidelines

No Comments

No Known Activations