INDEX

Explanations

programming-related function and method calls with a focus on JSON serialization and deserialization processes

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

tonode

-0.57

<bos>

-0.53

mstyle

-0.51

Rhestr

-0.49

sphase

-0.47

iastes

-0.45

 asset

-0.44

bledon

-0.43

TestBed

-0.43

jsii

-0.43

POSITIVE LOGITS

 kaynağından

0.88

 itſelf

0.80

 themſelves

0.76

 myſelf

0.72

$_"

0.72

."</

0.72

__":

0.70

modelBuilder

0.69

expandindo

0.67

.」

0.66

Activations Density 0.297%

programming-related function and method calls with a focus on JSON serialization and deserialization processes

No Comments

No Known Activations