INDEX

Explanations

mentions of the name "Niel" with varying levels of importance

oai_token-act-pair · gpt-3.5-turbo

proper names and specific identifiers related to individuals

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

ricular

-0.90

hedral

-0.81

rament

-0.68

ramid

-0.63

 odds

-0.61

ropolis

-0.61

urnal

-0.60

robat

-0.59

hered

-0.59

ctica

-0.59

POSITIVE LOGITS

ibrary

1.17

er

0.94

anguage

0.92

abel

0.89

vironment

0.86

ounge

0.81

le

0.80

iberal

0.79

naire

0.78

stadt

0.77

Activations Density 0.024%

mentions of the name "Niel" with varying levels of importance

proper names and specific identifiers related to individuals

No Comments

No Known Activations