INDEX

Explanations

conjunctions and phrases indicating relationships between concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 himself

-0.54

now

-0.53

lui

-0.52

 herself

-0.50

Them

-0.49

herself

-0.45

himself

-0.45

 really

-0.45

 siquiera

-0.44

 tiet

-0.43

POSITIVE LOGITS

 there

1.30

Искәрмәләр

0.91

 they

0.90

 ProtoMessage

0.89

there

0.87

tagHelperRunner

0.87

//}

0.85

مصادر

0.83

)))));

0.83

 nahilalakip

0.82

Activations Density 0.640%

conjunctions and phrases indicating relationships between concepts

No Comments

No Known Activations