INDEX

Explanations

references to input and output in the context of data processing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

IMPORTED

-0.79

 الاطلاع

-0.68

URLException

-0.63

 للمعارف

-0.63

HtmlAttribute

-0.62

hips

-0.59

ictwo

-0.56

SHIPS

-0.56

 importado

-0.56

reggio

-0.55

POSITIVE LOGITS

 output

0.88

output

0.78

 Output

0.74

 outcome

0.69

setOutput

0.67

Output

0.67

 outputs

0.67

argout

0.65

 result

0.63

 outcomes

0.62

Activations Density 0.522%

references to input and output in the context of data processing

No Comments

No Known Activations