INDEX

Explanations

phrases that introduce lists or explanations

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

AddTagHelper

-0.95

Portail

-0.74

 nargin

-0.74

AndEndTag

-0.74

Portale

-0.72

 насељу

-0.72

axy

-0.68

AccessFile

-0.67

enedig

-0.67

rrggbb

-0.66

POSITIVE LOGITS

 follows

0.83

 following

0.72

 يلي

0.71

follows

0.70

 suivant

0.66

如下

0.66

 suivantes

0.60

 şöyle

0.58

 következő

0.57

 suivante

0.57

Activations Density 0.372%

phrases that introduce lists or explanations

No Comments

No Known Activations