INDEX

Explanations

references to the word "clinal," indicating a focus on variations in biological or genetic traits along environmental gradients

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

AntiForgeryToken

-0.65

évaluateur

-0.64

LookAnd

-0.62

 تضيفلها

-0.59



-0.56

 pieno

-0.56

agisse

-0.55

참고

-0.55

 gynhyrchwyd

-0.52

 saiba

-0.51

POSITIVE LOGITS

Cl

0.59

Clo

0.58

Kl

0.57

CL

0.56

AsUp

0.56

anInt

0.54

Clu

0.53

rigos

0.52

 clothe

0.51

 noqa

0.51

Activations Density 0.171%

references to the word "clinal," indicating a focus on variations in biological or genetic traits along environmental gradients

No Comments

No Known Activations