INDEX

Explanations

sections or sentences identified as abstracts in academic papers

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

Par

-0.54

-0.52

<eos>

-0.50

 sport

-0.50

Con

-0.49

ch

-0.49

↵

-0.49

Con

-0.48

Al

-0.48

El

-0.48

POSITIVE LOGITS

</thead>

0.98

 myſelf

0.94

 jspb

0.93

Ass

0.92

MENAFN

0.90

Ass

0.90

../../../

0.90

zzleHttp

0.89

 poffible

0.88

 auffi

0.87

Activations Density 0.080%

sections or sentences identified as abstracts in academic papers

No Comments

No Known Activations