INDEX

Explanations

terms related to health statistics and medical conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.hook_resid_post

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

an

-0.70

ot

-0.66

端

-0.62

 domésticos

-0.62

 tấn

-0.61

arshal

-0.60

ン

-0.60

Documented

-0.60

salms

-0.60

richtet

-0.59

POSITIVE LOGITS

teness

0.96

Demografie

0.93

icity

0.91

izophrenia

0.89

ogeneity

0.89

cency

0.89

 Fitness

0.88

Fitness

0.87

Carcinogenicity

0.87

ibility

0.87

Activations Density 0.506%

terms related to health statistics and medical conditions

No Comments

No Known Activations