INDEX

Explanations

terms related to specific technical concepts or jargon in a structured format

oai_token-act-pair · gpt-3.5-turbo

specific keywords and terms related to various topics, likely focusing on technical or scientific jargon

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

accompan

-0.69

 Instr

-0.65

 Pric

-0.63

 Narr

-0.62

 Highlands

-0.61

 Seat

-0.61

å£«

-0.60

 Buddy

-0.59

 ultras

-0.58

 Accountability

-0.57

POSITIVE LOGITS

isoft

0.99

chwitz

0.94

mble

0.93

yssey

0.88

orm

0.84

uth

0.84

ead

0.83

ertain

0.81

cean

0.80

ircraft

0.79

Activations Density 0.116%

terms related to specific technical concepts or jargon in a structured format

specific keywords and terms related to various topics, likely focusing on technical or scientific jargon

No Comments

No Known Activations