INDEX

Explanations

terms related to adjustments and changes in context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

<em>

-0.51

-|-

-0.44

 object

-0.43

-0.42

<i>

-0.42

isMethod

-0.41

nanoTime

-0.40

-0.39

 institution

-0.38

getSimpleName

-0.38

POSITIVE LOGITS

 Tilt

0.65

 Adjusting

0.65

justed

0.64

Adjust

0.64

compensation

0.63

 Adjustments

0.63

adjust

0.62

 GenerationType

0.62

adjustment

0.61

 ModelExpression

0.61

Activations Density 0.851%

terms related to adjustments and changes in context

No Comments

No Known Activations

terms related to adjustments and changes in context

No Comments

No Known Activations