INDEX

Explanations

expressions of agreement or disagreement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

Personensuche

-0.67

indd

-0.63

GEBURTS

-0.62

Efq

-0.62

RenderAtEndOf

-0.62

InjectAttribute

-0.60

SharedCtor

-0.59

 parution

-0.58

yyl

-0.57

 "$@"

-0.56

POSITIVE LOGITS

Cyfeiriadau

0.71

 typelib

0.66

ynes

0.57

 kasarigan

0.52

Nope

0.51

Probably

0.50

 depende

0.50

 Nope

0.48

إنه

0.48

AxisAlignment

0.48

Activations Density 0.330%

expressions of agreement or disagreement

No Comments

No Known Activations