INDEX

Explanations

relationships and dynamics involving social connections and acceptance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.34.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

brigens

-0.58

новниш

-0.57

 propOrder

-0.54

colgante

-0.52

WireFormatLite

-0.48

 zuſammen

-0.48

ſſung

-0.48

antaranya

-0.48

uba

-0.48

 ſou

-0.47

POSITIVE LOGITS

 rather

4.31

 instead

3.84

rather

3.73

 plutôt

3.45

 Rather

3.45

instead

3.44

Rather

3.42

Instead

3.08

 Instead

3.05

 zamiast

3.05

Activations Density 2.770%

relationships and dynamics involving social connections and acceptance

No Comments

No Known Activations