INDEX

Explanations

proper nouns related to the name "Russ"

oai_token-act-pair · gpt-3.5-turbo

mentions of specific individuals or entities, particularly those associated with the name "Russ" or related variants

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

mable

-0.71

nce

-0.71

sections

-0.70

enment

-0.65

instance

-0.64

 conspicuous

-0.63

DER

-0.62

td

-0.61

$$

-0.61

District

-0.61

POSITIVE LOGITS

 Russ

0.92

akov

0.88

achev

0.88

aldo

0.86

kies

0.84

anova

0.84

illo

0.83

ault

0.83

kaya

0.80

Russ

0.80

Activations Density 0.018%

proper nouns related to the name "Russ"

mentions of specific individuals or entities, particularly those associated with the name "Russ" or related variants

No Comments

No Known Activations