INDEX

Explanations

terms related to biochemical processes, specifically focusing on inflammation and specific enzyme expressions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-mlp-16k

Configuration

google/gemma-scope-2b-pt-mlp/layer_6/width_16k/average_l0_133

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.hook_mlp_out

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

tru

-0.51

sam

-0.50

Sam

-0.49

 chosen

-0.49

ips

-0.49

相

-0.48

rag

-0.47

dic

-0.47

 pasos

-0.47

det

-0.46

POSITIVE LOGITS

 виправивши

0.96

TagMode

0.78

TargetException

0.77

Datuak

0.75

ISupport

0.74

ConstraintMaker

0.73

sidemargin

0.72

SourceChecksum

0.71

 kasarigan

0.69

tagHelperRunner

0.66

Activations Density 1.149%

terms related to biochemical processes, specifically focusing on inflammation and specific enzyme expressions

No Comments

No Known Activations