INDEX

Explanations

terms related to medical conditions and their effects on cognitive function

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

DoubleQuotes

-0.55

Cyfeiriadau

-0.54

 animés

-0.50

ynb

-0.48

ucleotide

-0.47

 Incenti

-0.46

anément

-0.45

 prome

-0.45

 препратки

-0.45

 borra

-0.45

POSITIVE LOGITS

Rüyada

0.72

RegressionTest

0.71

BufferException

0.69

 symptom

0.65

 diagnosis

0.64

 disease

0.63

 symptoms

0.62

TagMode

0.62

 SwitchCompat

0.61

 Cases

0.61

Activations Density 1.155%

terms related to medical conditions and their effects on cognitive function

No Comments

No Known Activations