INDEX

Explanations

references to figures and tables in a document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

----</

-0.73

 createSprite

-0.58

CodeAttribute

-0.58

+#+

-0.55

LikeLiked

-0.54

=*/

-0.53

CORBA

-0.53

SetBool

-0.51

putnik

-0.50

itattu

-0.50

POSITIVE LOGITS

 below

0.87

below

0.73

shows

0.66

 shows

0.63

 depicts

0.62

 bellow

0.62

 illustrates

0.62

 abaixo

0.61

PerformLayout

0.61

Tikang

0.61

Activations Density 0.550%

references to figures and tables in a document

No Comments

No Known Activations