INDEX

Explanations

references to specific proteins and immune-related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 kasarigan

-0.77

UnusedPrivate

-0.76

 '\\;'

-0.63

-0.59

 برانيه

-0.59

-0.58

Kariera

-0.55

principalTable

-0.54

Gator

-0.54

paksa

-0.52

POSITIVE LOGITS

DPM

1.21

JAM

1.18

CSM

1.17

SPM

1.16

BEM

1.16

BBM

1.15

LEM

1.14

HAM

1.13

APM

1.13

PSM

1.13

Activations Density 1.798%

references to specific proteins and immune-related terms

No Comments

No Known Activations