INDEX

Explanations

punctuation marks, specifically periods

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

antMatchers

-0.81

ientôt

-0.69

ionali

-0.68

 féminine

-0.68

 termica

-0.68

 zelve

-0.66

Kjelder

-0.66

imbawa

-0.66

 gevo

-0.66

zeptember

-0.65

POSITIVE LOGITS

0.69

 ModelExpression

0.64

\&

0.58

[toxicity=0]

0.56

nis

0.55

ectady

0.54

 AspNetCore

0.53

ugal

0.51

“

0.49

SerializedName

0.49

Activations Density 0.095%

punctuation marks, specifically periods

No Comments

No Known Activations