INDEX

Explanations

phrases and terms indicating positive effects, influences, or experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ResumeLayout

-0.60

__":

-0.54

 realistas

-0.53

Niz

-0.53

 Waray

-0.52

ndy

-0.52

entait

-0.51

 massless

-0.50

>>()

-0.49

 simplu

-0.48

POSITIVE LOGITS

прият

0.69

 EconPapers

0.66

 BoxDecoration

0.66

 favorably

0.65

twimg

0.64

 positive

0.64

 pleasant

0.62

 positively

0.61

 Posi

0.61

 favorable

0.59

Activations Density 0.386%

phrases and terms indicating positive effects, influences, or experiences

No Comments

No Known Activations