INDEX

Explanations

terms related to pharmacological and biochemical interactions in the context of neural activity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

ukan

-0.53

idom

-0.50

 Progress

-0.49

 Chand

-0.47

 Graf

-0.46

Rot

-0.46

 Lebens

-0.46

رش

-0.46

Progress

-0.46

품

-0.46

POSITIVE LOGITS

 GenerationType

1.01

цездатний

0.88

 propOrder

0.74

endpush

0.74

 Pharmacol

0.72

 MediatR

0.71

 useDispatch

0.70

 Мексичка

0.69

 pleaſure

0.65

 CreateTagHelper

0.65

Activations Density 0.998%

terms related to pharmacological and biochemical interactions in the context of neural activity

No Comments

No Known Activations