INDEX

Explanations

references to active listening and communication dynamics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

hyrchwyd

-0.55

 חיצוניים

-0.52

uxxxx

-0.52

otoro

-0.51

ectoria

-0.50

 Paix

-0.50

 samb

-0.50

ifilm

-0.50

WriteBarrier

-0.50

thday

-0.50

POSITIVE LOGITS

 listening

1.68

 listen

1.67

 listened

1.61

 listens

1.53

listening

1.43

 hearing

1.41

 Listen

1.36

 Listening

1.35

Listening

1.32

 hear

1.25

Activations Density 0.278%

references to active listening and communication dynamics

No Comments

No Known Activations