INDEX

Explanations

mentions of preferences or desires in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 createSlice

-1.02

IntoConstraints

-0.99

 AssemblyCulture

-0.95

存于互联网档案馆

-0.94

 سكانية

-0.92

complexContent

-0.91

NameInMap

-0.90

writeFieldEnd

-0.90

WithIOException

-0.88

Erreferentziak

-0.86

POSITIVE LOGITS

 likes

1.25

 needs

0.77

 wants

0.74

 loves

0.69

likes

0.66

 NEEDS

0.63

 Needs

0.60

 Likes

0.60

 knows

0.57

 Wants

0.56

Activations Density 0.210%

mentions of preferences or desires in the text

No Comments

No Known Activations