INDEX

Explanations

terms related to synaptic structures and neuronal signaling

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

MockBean

-0.45

Vors

-0.42

ētu

-0.42

 onCreateView

-0.42

NoSuchAlgorithm

-0.40

moveToFirst

-0.40

-0.39

 Nemesis

-0.36

ضى

-0.36

 ujednoznacz

-0.36

POSITIVE LOGITS

liesslich

0.73

HideFlags

0.72

nerf

0.71

脚注の使い方

0.69

المشاركات

0.68

faculty

0.66

 faculty

0.66

 comarca

0.65

Soorten

0.65

 насељу

0.64

Activations Density 2.803%

terms related to synaptic structures and neuronal signaling

No Comments

No Known Activations