INDEX

Explanations

numerical values in a range

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

op

-0.47

Biographie

-0.47

op

-0.46

fair

-0.45

 amables

-0.43

ی

-0.42

 fair

-0.42

disc

-0.42

Ek

-0.41

ville

-0.41

POSITIVE LOGITS

1.08

SequentialGroup

0.82

PerformLayout

0.76

 Eighth

0.76

 eighth

0.74

 NgModule

0.71

 vPvB

0.69

 octavo

0.69

aarrggbb

0.69

SharedCtor

0.68

Activations Density 0.074%

numerical values in a range

No Comments

No Known Activations