INDEX

Explanations

terms related to immune responses and cell signaling

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

extAlignment

-0.77

 članak

-0.71

 HomeController

-0.62

onOptions

-0.61

setArguments

-0.61

Géographie

-0.61

 Victims

-0.60

 Babylon

-0.59

DockStyle

-0.58

 places

-0.58

POSITIVE LOGITS

 Immunol

0.72

 immun

0.71

 immune

0.70

 inmun

0.67

 antibodies

0.67

 Immun

0.66

ApiModelProperty

0.66

 Immune

0.65

 Immunology

0.64

 immunological

0.62

Activations Density 1.385%

terms related to immune responses and cell signaling

No Comments

No Known Activations