INDEX

Explanations

phrases indicating locations and occurrences related to events or news

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 utafitiHapana

-0.71

ThroughAttribute

-0.62

lammatory

-0.59

 الوطنيه

-0.59

writeFieldEnd

-0.58

✨:

-0.58

MessageTagHelper

-0.58

 doccia

-0.58

phorbia

-0.57

jednoc

-0.56

POSITIVE LOGITS

__":

0.54

__':

0.46

ipto

0.43

._

0.42

Pyx

0.42

 nodding

0.41

documentclass

0.41

She

0.41

SharedModule

0.41

Activations Density 0.525%

phrases indicating locations and occurrences related to events or news

No Comments

No Known Activations