INDEX

Explanations

terms related to immune cell interactions and activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

/***/

-0.71

WriteTagHelper

-0.68

 дописавши

-0.64

]='\

-0.64

Personensuche

-0.61

onOptions

-0.61

CloseOperation

-0.61

 Houſe

-0.60

 виправивши

-0.60

 typelib

-0.59

POSITIVE LOGITS

 immune

0.99

 Immune

0.93

Immune

0.85

 Immunol

0.84

 Immunity

0.82

 имму

0.82

immune

0.81

 immunity

0.79

免疫

0.77

 Immunology

0.77

Activations Density 1.546%

terms related to immune cell interactions and activities

No Comments

No Known Activations