INDEX

Explanations

key phrases and terms related to medical testing and immune responses

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

Verbs followed by adjectives

np_acts-logits-general · gemini-2.0-flash

control and cause

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 things

-0.85

 coisas

-0.77

 cosas

-0.76

 stuff

-0.70

 thing

-0.69

 something

-0.69

 dingen

-0.68

-0.66

things

-0.65

POSITIVE LOGITS

$_"

1.04

$.

0.99

Efq

0.98

ſelf

0.98

)))));

0.95

 Jefus

0.92

Geplaatst

0.92

ftagPool

0.91

 myſelf

0.90

}}]{

0.89

Activations Density 4.982%

key phrases and terms related to medical testing and immune responses

Verbs followed by adjectives

control and cause

No Comments

No Known Activations