INDEX

Explanations

phrases related to comparison and evaluation

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

ubourg

-0.58

gette

-0.56

MLLoader

-0.55

timately

-0.53

醐

-0.53

 MediatR

-0.52

stonia

-0.52

inghouse

-0.52

tą

-0.51

 BorderRadius

-0.51

POSITIVE LOGITS

 comparison

4.27

 comparisons

3.79

 Comparison

3.78

 compare

3.68

 comparing

3.64

comparison

3.56

Comparison

3.52

 compares

3.46

 Comparisons

3.43

 compar

3.32

Activations Density 0.141%

phrases related to comparison and evaluation

No Comments

No Known Activations