INDEX

Explanations

specific named entities and technical terms, potentially related to data analysis or news reporting

oai_token-act-pair · gpt-3.5-turbo

specific names and classifications related to people, places, and data metrics

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

ãĥ£

-0.66

ived

-0.60

wx

-0.59

Merit

-0.59

rb

-0.59

Ô

-0.58

rss

-0.57

apa

-0.55

la

-0.55

ãĥŃ

-0.55

POSITIVE LOGITS

rul

0.78

 pouch

0.54

 coordinator

0.54

 condem

0.53

 guid

0.53

 nomine

0.52

 ported

0.52

 expel

0.52

 equivalents

0.51

 peripher

0.51

Activations Density 1.203%

specific named entities and technical terms, potentially related to data analysis or news reporting

specific names and classifications related to people, places, and data metrics

No Comments

No Known Activations