INDEX

Explanations

syntax related to error logging or messaging paths

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

berdayakan

-0.75

 BoxDecoration

-0.71

 Púb

-0.68

 pioggia

-0.68

 répon

-0.68

lewati

-0.66

 tropicales

-0.64

 Celui

-0.64

 parteci

-0.64

 esterno

-0.63

POSITIVE LOGITS

├──

0.68

0.66

con

0.65

0.64

mela

0.64

 commercial

0.63

 $("#

0.62

亨

0.61

$("#

0.61

 liquid

0.60

Activations Density 0.449%

syntax related to error logging or messaging paths

No Comments

No Known Activations