INDEX

Explanations

terms related to changes and modifications in processes or documents

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

 Roskov

-0.64

 doInBackground

-0.59

 GetEnumerator

-0.58

 opérateur

-0.55

SerializedName

-0.54

Климат

-0.54

adpleegd

-0.53

pozdrawiam

-0.53

intios

-0.52

idemia

-0.52

POSITIVE LOGITS

 change

1.05

Changing

1.02

 changing

0.99

 changes

0.97

change

0.94

 Changing

0.94

 Change

0.92

Change

0.91

changing

0.88

 Changes

0.88

Activations Density 0.408%

terms related to changes and modifications in processes or documents

No Comments

No Known Activations