INDEX

Explanations

references to media and events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

netinet

-0.64

ädchen

-0.60

 opdracht

-0.59

databind

-0.58

ędziesz

-0.58

uminen

-0.56

APOLIS

-0.55

GroupLayout

-0.55

 coute

-0.54

quehanna

-0.53

POSITIVE LOGITS

 своим

0.59

 своей

0.57

abestanden

0.55

NameInMap

0.53

<bos>

0.53

 shar

0.51

 introducing

0.49

ops

0.49

 svým

0.48

mez

0.48

Activations Density 0.231%

references to media and events

No Comments

No Known Activations