INDEX

Explanations

quantitative descriptors and approximations in relation to statistics or measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

 EconPapers

-0.83

ⓧ

-0.82

 للمعارف

-0.82

 AssemblyTitle

-0.80

 InputDecoration

-0.75

 BoxDecoration

-0.74

+#+#

-0.72

참고

-0.69

ագրություններ

-0.66

 himo

-0.65

POSITIVE LOGITS

 four

0.61

 eight

0.59

 seven

0.59

 three

0.58

six

0.56

]='\

0.55

 grun

0.54

 five

0.53

 double

0.53

Activations Density 0.139%

quantitative descriptors and approximations in relation to statistics or measurements

No Comments

No Known Activations