INDEX

Explanations

references to tuning or adjustments in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

rics

-0.61

 useAppContext

-0.59

gående

-0.59

 giustizia

-0.58

{}/

-0.58

 Gerechtigkeit

-0.56

 Schindler

-0.55

 مشين

-0.55

 Bassi

-0.54

../../../

-0.53

POSITIVE LOGITS

 tune

1.03

 Tune

1.00

 tuning

0.95

Tune

0.94

Tun

0.91

tune

0.88

Tun

0.84

 Tuning

0.81

 tuned

0.81

TUN

0.79

Activations Density 0.042%

references to tuning or adjustments in various contexts

No Comments

No Known Activations