INDEX

Explanations

terms related to data analysis and academic studies

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

setDo

-0.58

IsContent

-0.52

Legături

-0.50

AndEndTag

-0.48

SourceChecksum

-0.48

ütfen

-0.47

 виправивши

-0.47

ESOME

-0.46

fetchone

-0.45

PageRoute

-0.45

POSITIVE LOGITS

########.

0.85

httphttps

0.76

CodeAttribute

0.69

 CYTHON

0.61

 Lexicon

0.59

MessageTagHelper

0.59

={({

0.56

 BIBSYS

0.55

+#+

0.55

 AssemblyCompany

0.55

Activations Density 0.885%

terms related to data analysis and academic studies

No Comments

No Known Activations