INDEX

Explanations

components related to data manipulation in Python, particularly using pandas and R

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

RectangleBorder

-1.13

-1.00

Tikang

-0.95

SourceChecksum

-0.93

 AssemblyProduct

-0.92

 חיצוניים

-0.91

 resourceCulture

-0.89

 onAnimation

-0.88

contentLoaded

-0.87

GrantedAuthority

-0.84

POSITIVE LOGITS

 pandas

0.71

DataFrame

0.71

0.66

pandas

0.60

df

0.56

dataframe

0.56

 DataFrame

0.49

pd

0.48

 table

0.48

Activations Density 0.145%

components related to data manipulation in Python, particularly using pandas and R

No Comments

No Known Activations