INDEX

Explanations

verbs and phrases related to unresolved actions or processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

ิลปะ

-0.63

 kohta

-0.54

 Surplus

-0.53

 utafitiHapana

-0.53

beelden

-0.52

 Quasi

-0.52

 valuta

-0.51

égias

-0.51

 Langford

-0.50

binant

-0.50

POSITIVE LOGITS

 decked

0.85

 مشين

0.84

 blown

0.84

 blow

0.83

%")

0.81

 geared

0.80

 shuts

0.80

ghed

0.80

 handed

0.80

 оригіналу

0.79

Activations Density 0.465%

verbs and phrases related to unresolved actions or processes

No Comments

No Known Activations