INDEX

Explanations

sentences that involve communication and explanation of procedures or details

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



-0.64

ftagPool

-0.58

assertj

-0.55

IComponent

-0.53

 administrativos

-0.53

 MonoBehaviour

-0.52

 kasarigan

-0.51

qrstuvwxyz

-0.51

 retenir

-0.50

Activator

-0.50

POSITIVE LOGITS

 explaining

1.16

 explain

1.14

 explained

1.09

 told

1.07

 telling

1.02

Told

1.00

 Explain

0.98

Explain

0.98

 tell

0.98

Tell

0.95

Activations Density 0.455%

sentences that involve communication and explanation of procedures or details

No Comments

No Known Activations