INDEX

Explanations

specific terms related to events, locations, or individuals tied to educational or legal contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

Efq

-0.80

 becauſe

-0.79

 Theſe

-0.78

 متعلقه

-0.78

 myſelf

-0.78

 ―――――

-0.78

 Monfieur

-0.77

 ſche

-0.77

ſelf

-0.75

 houſe

-0.75

POSITIVE LOGITS

已经是

0.57

 برانيه

0.57

已是

0.56

Ĝ

0.54

何より

0.53

numerusform

0.53

sizeof

0.53

igshid

0.51

ئيس

0.51

orari

0.50

Activations Density 2.675%

specific terms related to events, locations, or individuals tied to educational or legal contexts

No Comments

No Known Activations