INDEX

Explanations

responses indicating perception or assessment regarding experiences or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.36.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

msgTypes

-0.57



-0.57

 isNameExpr

-0.48

ỡng

-0.47

MessageOf

-0.47

FormTagHelper

-0.47

قایناقلار

-0.46

WriteTagHelper

-0.45

BagConstraints

-0.45

ensdag

-0.45

POSITIVE LOGITS

 like

3.98

 Like

2.80

 LIKE

2.56

Like

2.55

like

2.45

 seperti

2.38

 như

2.17

 zoals

2.02

 como

2.00

 مانند

1.94

Activations Density 2.268%

responses indicating perception or assessment regarding experiences or events

No Comments

No Known Activations