INDEX

Explanations

references to the pandas library and DataFrame objects in programming contexts

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

 capp

-0.65

roslav

-0.60

 Waray

-0.57

Ê

-0.57

 Bubble

-0.55

deter

-0.55

egg

-0.54

 Rued

-0.53

 Scramble

-0.53

 Winchester

-0.53

POSITIVE LOGITS

pd

2.74

pd

2.49

PD

2.42

PD

2.34

Pd

1.55

Pd

1.45

PDG

1.17

PDS

0.99

PDP

0.96

BPD

0.95

Activations Density 0.092%

references to the pandas library and DataFrame objects in programming contexts

No Comments

No Known Activations