INDEX

Explanations

references to connections and relationships between concepts or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

Carriera

-0.60

ifflin

-0.55

Filmographie

-0.55

ionales

-0.54

setDo

-0.53

irited

-0.52

 poffible

-0.51

 fhort

-0.50

 poffe

-0.50

aság

-0.49

POSITIVE LOGITS

 كومونز

0.64

تقاوى

0.56

AutoScaleMode

0.55

atissimo

0.54

igreja

0.54

 terceiros

0.54

ddots

0.53

albeit

0.51

+#+#

0.51

\}\\

0.51

Activations Density 0.439%

references to connections and relationships between concepts or entities

No Comments

No Known Activations