INDEX

Explanations

mentions or references to the news outlet "RT"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the abbreviation "RT," likely indicating retweets or references to other sources in social media contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

iasis

-0.84

ãĤ©

-0.68

tained

-0.67

alities

-0.67

rera

-0.65

erved

-0.63

 coron

-0.62

 incent

-0.62

[|

-0.61

cised

-0.61

POSITIVE LOGITS

Ãī

1.14

irtual

0.89

TY

0.82

PC

0.80

TE

0.80

IA

0.79

BF

0.78

ython

0.78

LM

0.77

RT

0.77

Activations Density 0.014%

mentions or references to the news outlet "RT"

occurrences of the abbreviation "RT," likely indicating retweets or references to other sources in social media contexts

No Comments

No Known Activations