INDEX

Explanations

terms related to noise and properties of signals in data analysis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

gonic

-0.56

IsContent

-0.50

 springfox

-0.49

ldc

-0.47

éndole

-0.45

illary

-0.45

PullParser

-0.45

 GoogleFonts

-0.44

multicolumn

-0.43

KindOfClass

-0.43

POSITIVE LOGITS

thâu

0.69

новниш

0.67

expandindo

0.67

 ویکی‌پدیای

0.66

BufferException

0.65

 propOrder

0.63

➟

0.62

يديا

0.61

 sinon

0.61

onAttach

0.60

Activations Density 0.384%

terms related to noise and properties of signals in data analysis

No Comments

No Known Activations