INDEX

Explanations

occurrences of loop control variables in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.34.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

✭✭

-0.62

IVEREF

-0.58

-------

-0.57

 linkovi

-0.52

SourceChecksum

-0.51

Manbalar

-0.50

NUMX

-0.49

GTCX

-0.47

 tartalomajánló

-0.46

expandindo

-0.45

POSITIVE LOGITS

 short

1.09

short

1.00

Short

0.91

 Short

0.90

 SHORT

0.85

SHORT

0.81

 fhort

0.70

shy

0.69

 krótk

0.63

 kurzen

0.60

Activations Density 0.171%

occurrences of loop control variables in code

No Comments

No Known Activations

occurrences of loop control variables in code

No Comments

No Known Activations