INDEX

Explanations

terms related to output and data handling, particularly in technical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 صوتيه

-0.84

ValueStyle

-0.71

 betweenstory

-0.70

UnusedPrivate

-0.64

 puissiez

-0.63

>{@

-0.63

 فريبيس

-0.63

IANGLES

-0.61

 चीज़ों

-0.61

 Waray

-0.61

POSITIVE LOGITS

lier

0.59

Put

0.58

DOOR

0.56

 loud

0.54

doors

0.54

going

0.53

 bound

0.53

GOING

0.52

[]:

0.52

liers

0.51

Activations Density 0.162%

terms related to output and data handling, particularly in technical contexts

No Comments

No Known Activations