INDEX

Explanations

terms indicating representation or indicators related to populations and their characteristics over time

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

dflare

-0.43

ệc

-0.40

 rapat

-0.40

ouvrage

-0.39

⟬

-0.38

strconv

-0.38

 paradox

-0.38

jardins

-0.37

AddTagHelper

-0.36

 confiance

-0.35

POSITIVE LOGITS

Met

0.47

 getItemCount

0.42

انجليز

0.42

spath

0.42

pied

0.41

atisk

0.41

MET

0.41

Met

0.40

WindowConstants

0.39

met

0.39

Activations Density 0.088%

terms indicating representation or indicators related to populations and their characteristics over time

No Comments

No Known Activations