INDEX

Explanations

words related to active processes or states involving movement and connection

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

-0.59

-0.52

варь

-0.51

is

-0.49

-0.48

-0.46

 nostru

-0.45

",

-0.45

 alimentaires

-0.45

ia

-0.44

POSITIVE LOGITS

 فريبيس

0.79

BufferException

0.72

lynol

0.72

ThroughAttribute

0.72

Gambas

0.71

FormTagHelper

0.71

 hObject

0.71

APORE

0.71

twimg

0.70

 ErrIntOverflow

0.70

Activations Density 0.833%

words related to active processes or states involving movement and connection

No Comments

No Known Activations