INDEX

Explanations

concepts related to psychological and social frameworks, particularly surrounding gender dynamics and communication

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 propOrder

-0.65

ίσ

-0.52

squareup

-0.52

AVAN

-0.50

hitting

-0.50

μισ

-0.50

inephrine

-0.49

 coû

-0.49

 épar

-0.48

วา

-0.48

POSITIVE LOGITS

 function

0.59

 functions

0.59

 problem

0.57

problem

0.57

 mediate

0.56

 privileges

0.56

 legitimate

0.55

الإنجليزية

0.54

functions

0.53

function

0.53

Activations Density 0.390%

concepts related to psychological and social frameworks, particularly surrounding gender dynamics and communication

No Comments

No Known Activations