INDEX

Explanations

mentions of action-oriented content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 devenus

-0.67

brtc

-0.63

 TextInputType

-0.62

crollView

-0.61

 vettoriale

-0.61

ScopeManager

-0.59

 produisons

-0.58

UnknownFields

-0.57

 fermés

-0.56

withIdentifier

-0.56

POSITIVE LOGITS

 action

5.20

 Action

4.56

action

4.39

Action

4.26

 ACTION

4.15

ACTION

3.54

 actions

3.41

 acción

3.35

 Actions

3.24

actions

2.90

Activations Density 0.107%

mentions of action-oriented content

No Comments

No Known Activations