INDEX

Explanations

formal medical classification terms related to psychological disorders

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

uffff

-0.55

chiali

-0.52

WireFormatLite

-0.48

complexContent

-0.47

eltjes

-0.46

érience

-0.45

zös

-0.45

 Chez

-0.44

cse

-0.44

nolia

-0.44

POSITIVE LOGITS

 codes

1.01

 code

0.91

 Codes

0.88

Codes

0.85

codes

0.85

 códigos

0.83

code

0.83

 coding

0.78

 getCode

0.77

Code

0.76

Activations Density 0.203%

formal medical classification terms related to psychological disorders

No Comments

No Known Activations