INDEX

Explanations

terms related to comprehension and definition

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Roskov

-1.01

 насељу

-0.97

AndEndTag

-0.97

ioutil

-0.85

ModelSerializer

-0.83

 beginnetje

-0.82

principalTable

-0.81

 صوتيه

-0.81

 Италијани

-0.80

Datuak

-0.79

POSITIVE LOGITS

 atve

0.48

場合

0.47

 standpoint

0.47

 insofar

0.44

 purposes

0.43

 anlam

0.42

する場合

0.42

 terms

0.41

而言

0.41

 regarded

0.41

Activations Density 0.410%

terms related to comprehension and definition

No Comments

No Known Activations

terms related to comprehension and definition

No Comments

No Known Activations