INDEX

Explanations

terms related to specific entities or locations

oai_token-act-pair · gpt-3.5-turbo

specific topics or categories within scientific and geographic content

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

mble

-0.78

aukee

-0.70

*/(

-0.68

cffffcc

-0.63

!".

-0.61

 destro

-0.61

."[

-0.60

oldown

-0.59

etsk

-0.58

Ń·

-0.58

POSITIVE LOGITS

FK

0.59

 Newsp

0.59

 Blaz

0.55

involved

0.55

 relating

0.55

 related

0.54

 versus

0.53

 Literature

0.52

 handwriting

0.51

 websites

0.51

Activations Density 0.720%

terms related to specific entities or locations

specific topics or categories within scientific and geographic content

No Comments

No Known Activations